The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integra...The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integrates transformer-based models(RoBERTa)and large language models(LLMs)(GPT-OSS 120B,LLaMA3.370B,and Qwen332B)to enhance smishing detection performance significantly.To mitigate class imbalance,we apply synthetic data augmentation using T5 and leverage various text preprocessing techniques.Our system employs a duallayer voting mechanism:weighted majority voting among LLMs and a final ensemble vote to classify messages as ham,spam,or smishing.Experimental results show an average accuracy improvement from 96%to 98.5%compared to the best standalone transformer,and from 93%to 98.5%when compared to LLMs across datasets.Furthermore,we present a real-time,user-friendly application to operationalize our detection model for practical use.PhishNet demonstrates superior scalability,usability,and detection accuracy,filling critical gaps in current smishing detection methodologies.展开更多
Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.Howev...Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.展开更多
Zero-click attacks represent an advanced cybersecurity threat,capable of compromising devices without user interaction.High-profile examples such as Pegasus,Simjacker,Bluebugging,and Bluesnarfing exploit hidden vulner...Zero-click attacks represent an advanced cybersecurity threat,capable of compromising devices without user interaction.High-profile examples such as Pegasus,Simjacker,Bluebugging,and Bluesnarfing exploit hidden vulnerabilities in software and communication protocols to silently gain access,exfiltrate data,and enable long-term surveillance.Their stealth and ability to evade traditional defenses make detection and mitigation highly challenging.This paper addresses these threats by systematically mapping the tactics and techniques of zero-click attacks using the MITRE ATT&CK framework,a widely adopted standard for modeling adversarial behavior.Through this mapping,we categorize real-world attack vectors and better understand how such attacks operate across the cyber-kill chain.To support threat detection efforts,we propose an Active Learning-based method to efficiently label the Pegasus spyware dataset in alignment with the MITRE ATT&CK framework.This approach reduces the effort of manually annotating data while improving the quality of the labeled data,which is essential to train robust cybersecurity models.In addition,our analysis highlights the structured execution paths of zero-click attacks and reveals gaps in current defense strategies.The findings emphasize the importance of forward-looking strategies such as continuous surveillance,dynamic threat profiling,and security education.By bridging zero-click attack analysis with the MITRE ATT&CK framework and leveraging machine learning for dataset annotation,this work provides a foundation for more accurate threat detection and the development of more resilient and structured cybersecurity frameworks.展开更多
Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Althoug...Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.展开更多
With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comp...With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.展开更多
The exponential growth of the Internet of Things(IoT)has introduced significant security challenges,with zero-day attacks emerging as one of the most critical and challenging threats.Traditional Machine Learning(ML)an...The exponential growth of the Internet of Things(IoT)has introduced significant security challenges,with zero-day attacks emerging as one of the most critical and challenging threats.Traditional Machine Learning(ML)and Deep Learning(DL)techniques have demonstrated promising early detection capabilities.However,their effectiveness is limited when handling the vast volumes of IoT-generated data due to scalability constraints,high computational costs,and the costly time-intensive process of data labeling.To address these challenges,this study proposes a Federated Learning(FL)framework that leverages collaborative and hybrid supervised learning to enhance cyber threat detection in IoT networks.By employing Deep Neural Networks(DNNs)and decentralized model training,the approach reduces computational complexity while improving detection accuracy.The proposed model demonstrates robust performance,achieving accuracies of 94.34%,99.95%,and 87.94%on the publicly available kitsune,Bot-IoT,and UNSW-NB15 datasets,respectively.Furthermore,its ability to detect zero-day attacks is validated through evaluations on two additional benchmark datasets,TON-IoT and IoT-23,using a Deep Federated Learning(DFL)framework,underscoring the generalization and effectiveness of the model in heterogeneous and decentralized IoT environments.Experimental results demonstrate superior performance over existing methods,establishing the proposed framework as an efficient and scalable solution for IoT security.展开更多
Ballet is one of the finalists of the block cipher project in the 2019 National Cryptographic Algorithm Design Competition.This study aims to conduct a comprehensive security evaluation of Ballet from the perspective ...Ballet is one of the finalists of the block cipher project in the 2019 National Cryptographic Algorithm Design Competition.This study aims to conduct a comprehensive security evaluation of Ballet from the perspective of differential-linear(DL)cryptanalysis.Specifically,we present an automated search for the DL distinguishers of Ballet based on MILP/MIQCP.For the versions with block sizes of 128 and 256 bits,we obtain 16 and 22 rounds distinguishers with estimated correlations of 2^(-59.89)and 2^(-116.80),both of which are the publicly longest distinguishers.In addition,this study incorporates the complexity information of key-recovery attacks into the automated model,to search for the optimal key-recovery attack structures based on DL distinguishers.As a result,we mount the key-recovery attacks on 16-round Ballet-128/128,17-round Ballet-128/256,and 21-round Ballet-256/256.The data/time complexities for these attacks are 2^(108.36)/2^(120.36),2^(115.90)/2^(192),and 2^(227.62)/2^(240.67),respectively.展开更多
Asymmetric cryptographic schemes, represe nted by RSA, have bee n show n to be in secure un der quantum computing conditions. Correspondingly, there is a need to study whether the symmetric cryptosystem can still guar...Asymmetric cryptographic schemes, represe nted by RSA, have bee n show n to be in secure un der quantum computing conditions. Correspondingly, there is a need to study whether the symmetric cryptosystem can still guarantee high security with the advent of quantum computers. In this paper, based on the basic principles of classical slide attacks and Simon's algorithm, we take LED-like lightweight block ciphers as research objects to present a security analysis under both classical and quantum attacks, fully considering the influence on the security of the ciphers of adding the round constants. By analyzing the information leakage of round constants, we can introduce the differential of the round constants to propose a classical slide attack on full-round LED-64 with a probability of 1. The analysis result shows that LED-64 is unable to resist this kind of classical slide attack, but that attack method is not applicable to LED-128. As for quantum attacks, by improving on existing quantum attack methods we dem on strate a qua ntum single-key slide attack on LED-64 and a quantum related-key attack on LED- 128, and indicators of the two attack algorithms are analyzed in detail. The attack results show that adding round consta nts does not completely improve the security of the ciphers, and quantum attacks can provide an exp on ential speed-up over the same attacks in the classical model. It further illustrates that the block cipher that is proved to be safe under classical settings is not necessarily secure under quantum conditions.展开更多
In EUROCRYPT 2017,a new structure-difference property,say“a-multiple-of-8”was proposed on 5-round AES.Inspired by the idea,yoyo attacks and mixture differential attacks were proposed yielding new records on data and...In EUROCRYPT 2017,a new structure-difference property,say“a-multiple-of-8”was proposed on 5-round AES.Inspired by the idea,yoyo attacks and mixture differential attacks were proposed yielding new records on data and computational complexities for key-recovery attacks against 5-round AES.In this paper,the authors attempt to apply the idea of mixture differential cryptanalysis to Midori64.Midori is a lightweight block cipher proposed at ASIACRYPT 2015.Although the structure of Midori is similar to AES,the MixColumn matrix of Midori is not MDS.Based on this observation,the authors present a class of deterministic differential trails on 2-round Midori.Then combined with the yoyo trick,a new type of 4-round retracing boomerang distinguishers is obtained on Midori.Based on the new 4-round distinguishers,a key-recovery attack on 6-round Midori64 is given that requires only 2^(27)computational complexity,2^(29)chosen plaintexts,2^(20)adaptively chosen ciphertexts.The key-recovery attack has been experimentally verified.展开更多
In ASIACCS 2015, Nu nez, et al. proposed a proxy re-encryption scheme, named NTRURe Encrypt, based on NTRU, which allows a proxy to translate ciphertext under the delegator’s public key into a re-encrypted ciphertext...In ASIACCS 2015, Nu nez, et al. proposed a proxy re-encryption scheme, named NTRURe Encrypt, based on NTRU, which allows a proxy to translate ciphertext under the delegator’s public key into a re-encrypted ciphertext that can be decrypted correctly by delegatee’s private key. Because of the potential resistance to quantum algorithm, high efficiency and various applications in real life,NTRURe Encrypt has drawn lots of attention and its security has been widely discussed and analyzed.In PQCrypto2019, Liu, et al. proposed two key recovery attacks against it. However, their first attack heavily relies on a weaken decryption oracle, and the second attack needs to collect about 260ciphertexts from the same message by theoretical analysis, which makes both of the attacks unrealistic. In this paper, inspired by the broadcast attack against NTRU, the authors find out that for NTRURe Encrypt the delegator and the delegatee can efficiently recover each other’s private key in polynomial time without any unrealistic assumptions. In addition, the authors also show how to fix NTRURe Encrypt to resist the proposed attacks. As a by-product, the authors also show how to commit broadcast attacks against NTRU 2001 with even dg, which was thought infeasible before.展开更多
This paper addresses the consensus problem of nonlinear multi-agent systems subject to external disturbances and uncertainties under denial-ofservice(DoS)attacks.Firstly,an observer-based state feedback control method...This paper addresses the consensus problem of nonlinear multi-agent systems subject to external disturbances and uncertainties under denial-ofservice(DoS)attacks.Firstly,an observer-based state feedback control method is employed to achieve secure control by estimating the system's state in real time.Secondly,by combining a memory-based adaptive eventtriggered mechanism with neural networks,the paper aims to approximate the nonlinear terms in the networked system and efficiently conserve system resources.Finally,based on a two-degree-of-freedom model of a vehicle affected by crosswinds,this paper constructs a multi-unmanned ground vehicle(Multi-UGV)system to validate the effectiveness of the proposed method.Simulation results show that the proposed control strategy can effectively handle external disturbances such as crosswinds in practical applications,ensuring the stability and reliable operation of the Multi-UGV system.展开更多
Watermarking is embedding visible or invisible data within media to verify its authenticity or protect copyright.The watermark is embedded in significant spatial or frequency features of the media to make it more resi...Watermarking is embedding visible or invisible data within media to verify its authenticity or protect copyright.The watermark is embedded in significant spatial or frequency features of the media to make it more resistant to intentional or unintentional modification.Some of these features are important perceptual features according to the human visual system(HVS),which means that the embedded watermark should be imperceptible in these features.Therefore,both the designers of watermarking algorithms and potential attackers must consider these perceptual features when carrying out their actions.The two roles will be considered in this paper when designing a robust watermarking algorithm against the most harmful attacks,like volumetric scaling,histogram equalization,and non-conventional watermarking attacks like the Denoising Convolution Neural Network(DnCNN),which must be considered in watermarking algorithm design due to its rising role in the state-of-the-art attacks.The DnCNN is initialized and trained using watermarked image samples created by our proposed Covert and Severe Attacks Resistant Watermarking Algorithm(CSRWA)to prove its robustness.For this algorithm to satisfy the robustness and imperceptibility tradeoff,implementing the Dither Modulation(DM)algorithm is boosted by utilizing the Just Noticeable Distortion(JND)principle to get an improved performance in this sense.Sensitivity,luminance,inter and intra-block contrast are used to adjust the JND values.展开更多
The rapid proliferation of electric vehicle(EV)charging infrastructure introduces critical cybersecurity vulnerabilities to power grids system.This study presents an innovative anomaly detection framework for EV charg...The rapid proliferation of electric vehicle(EV)charging infrastructure introduces critical cybersecurity vulnerabilities to power grids system.This study presents an innovative anomaly detection framework for EV charging stations,addressing the unique challenges posed by third-party aggregation platforms.Our approach integrates node equations-based on the parameter identification with a novel deep learning model,xDeepCIN,to detect abnormal data reporting indicative of aggregation attacks.We employ a graph-theoretic approach to model EV charging networks and utilize Markov Chain Monte Carlo techniques for accurate parameter estimation.The xDeepCIN model,incorporating a Compressed Interaction Network,has the ability to capture complex feature interactions in sparse,high-dimensional charging data.Experimental results on both proprietary and public datasets demonstrate significant improvements in anomaly detection performance,with F1-scores increasing by up to 32.3%for specific anomaly types compared to traditional methods,such as wide&deep and DeepFM(Factorization-Machine).Our framework exhibits robust scalability,effectively handling networks ranging from 8 to 85 charging points.Furthermore,we achieve real-time monitoring capabilities,with parameter identification completing within seconds for networks up to 1000 nodes.This research contributes to enhancing the security and reliability of renewable energy systems against evolving cyber threats,offering a comprehensive solution for safeguarding the rapidly expanding EV charging infrastructure.展开更多
Sulfate attack-induced expansion of cement-treated aggregates in seasonally frozen regions is a well-known issue which causes continuous expansion in railway subgrades,and particularly in high-speed railways.According...Sulfate attack-induced expansion of cement-treated aggregates in seasonally frozen regions is a well-known issue which causes continuous expansion in railway subgrades,and particularly in high-speed railways.Accordingly,we investigated the influence of material proportions,the number of freeze-thaw(FT)cycles,and temperature gradients on the expansion mechanism of sulfate attack on cement-treated aggregates subjected to FT cycles.The conditions,laws,and dominant factors causing the expansion of aggregates were analyzed through swelling tests.The results indicate that under FT cycles,3%content cement-treated graded macadam only experiences slight deformation.The maximum strain of graded macadam attacked by 1%sodium sulfate content in each FT cycle is significantly larger than that of 3%content cement-treated graded macadam attacked by 1%sodium sulfate content.Using scanning electron microscopy,needle-like crystals were observed during sulfate attack of cement-treated graded macadam.Through quantitative analysis,we determined the recoverable and unrecoverable deformations of graded macadam under FT cycles.For graded macadam under sulfate attack,the expansion is mainly induced by periodic frost heave and salt expansion,as well as salt migration.For cement-treated graded macadam under sulfate attack,the expansion is mainly induced by chemical attack and salt migration.This study can serve as a reference for future research on the mechanics of sulfate attack on cement-treated aggregates that experience FT cycles,and provide theoretical support for methods that remediate the expansion induced by sulfate attack.展开更多
Unsteady aerodynamic characteristics at high angles of attack are of great importance to the design and development of advanced fighter aircraft, which are characterized by post-stall maneuverability with multiple Deg...Unsteady aerodynamic characteristics at high angles of attack are of great importance to the design and development of advanced fighter aircraft, which are characterized by post-stall maneuverability with multiple Degrees-of-Freedom(multi-DOF) and complex flow field structure.In this paper, a special kind of cable-driven parallel mechanism is firstly utilized as a new suspension method to conduct unsteady dynamic wind tunnel tests at high angles of attack, thereby providing experimental aerodynamic data. These tests include a wide range of multi-DOF coupled oscillatory motions with various amplitudes and frequencies. Then, for aerodynamic modeling and analysis, a novel data-driven Feature-Level Attention Recurrent neural network(FLAR) is proposed. This model incorporates a specially designed feature-level attention module that focuses on the state variables affecting the aerodynamic coefficients, thereby enhancing the physical interpretability of the aerodynamic model. Subsequently, spin maneuver simulations, using a mathematical model as the baseline, are conducted to validate the effectiveness of the FLAR. Finally, the results on wind tunnel data reveal that the FLAR accurately predicts aerodynamic coefficients, and observations through the visualization of attention scores identify the key state variables that affect the aerodynamic coefficients. It is concluded that the proposed FLAR enhances the interpretability of the aerodynamic model while achieving good prediction accuracy and generalization capability for multi-DOF coupling motion at high angles of attack.展开更多
The paper presents experimental investigation results of crack pattern change in cement pastes caused by external sulfate attack(ESA).To visualize the formation and development of cracks in cement pastes under ESA,an ...The paper presents experimental investigation results of crack pattern change in cement pastes caused by external sulfate attack(ESA).To visualize the formation and development of cracks in cement pastes under ESA,an X-ray computed tomography(X-ray CT)was used,i e,the tomography system of Zeiss Xradia 510 versa.The results indicate that X-CT can monitor the development process and distribution characteristics of the internal cracks of cement pastes under ESA with attack time.In addition,the C3A content in the cement significantly affects the damage mode of cement paste specimens during sulfate erosion.The damage of ordinary Portland cement(OPC)pastes subjected to sulfate attack with high C3A content are severe,while the damage of sulfate resistant Portland cement(SRPC)pastes is much smaller than that of OPC pastes.Furthermore,a quadratic function describes the correlation between the crack volume fraction and development depth for two cement pastes immermed in sulfate solution.展开更多
To improve the vertical axis wind turbine(VAWT)design,the angle of attack(AOA)and airfoil data must be treated correctly.The present paper develops a method for determining AOA on a VAWT based on computational fluid d...To improve the vertical axis wind turbine(VAWT)design,the angle of attack(AOA)and airfoil data must be treated correctly.The present paper develops a method for determining AOA on a VAWT based on computational fluid dynamics(CFD)analysis.First,a CFD analysis of a two-bladed VAWT equipped with a NACA 0012 airfoil is conducted.The thrust and power coefficients are validated through experiments.Second,the blade force and velocity data at monitoring points are collected.The AOA at different azimuth angles is determined by removing the blade self-induction at the monitoring point.Then,the lift and drag coefficients as a function of AOA are extracted.Results show that this method is independent of the monitoring points selection located at certain distance to the blades and the extracted dynamic stall hysteresis is more precise than the one with the“usual”method without considering the self-induction from bound vortices.展开更多
Previous studies have shown that deep learning is very effective in detecting known attacks.However,when facing unknown attacks,models such as Deep Neural Networks(DNN)combined with Long Short-Term Memory(LSTM),Convol...Previous studies have shown that deep learning is very effective in detecting known attacks.However,when facing unknown attacks,models such as Deep Neural Networks(DNN)combined with Long Short-Term Memory(LSTM),Convolutional Neural Networks(CNN)combined with LSTM,and so on are built by simple stacking,which has the problems of feature loss,low efficiency,and low accuracy.Therefore,this paper proposes an autonomous detectionmodel for Distributed Denial of Service attacks,Multi-Scale Convolutional Neural Network-Bidirectional Gated Recurrent Units-Single Headed Attention(MSCNN-BiGRU-SHA),which is based on a Multistrategy Integrated Zebra Optimization Algorithm(MI-ZOA).The model undergoes training and testing with the CICDDoS2019 dataset,and its performance is evaluated on a new GINKS2023 dataset.The hyperparameters for Conv_filter and GRU_unit are optimized using the Multi-strategy Integrated Zebra Optimization Algorithm(MIZOA).The experimental results show that the test accuracy of the MSCNN-BiGRU-SHA model based on the MIZOA proposed in this paper is as high as 0.9971 in the CICDDoS 2019 dataset.The evaluation accuracy of the new dataset GINKS2023 created in this paper is 0.9386.Compared to the MSCNN-BiGRU-SHA model based on the Zebra Optimization Algorithm(ZOA),the detection accuracy on the GINKS2023 dataset has improved by 5.81%,precisionhas increasedby 1.35%,the recallhas improvedby 9%,and theF1scorehas increasedby 5.55%.Compared to the MSCNN-BiGRU-SHA models developed using Grid Search,Random Search,and Bayesian Optimization,the MSCNN-BiGRU-SHA model optimized with the MI-ZOA exhibits better performance in terms of accuracy,precision,recall,and F1 score.展开更多
The intelligent operation management of distribution services is crucial for the stability of power systems.Integrating the large language model(LLM)with 6G edge intelligence provides customized management solutions.H...The intelligent operation management of distribution services is crucial for the stability of power systems.Integrating the large language model(LLM)with 6G edge intelligence provides customized management solutions.However,the adverse effects of false data injection(FDI)attacks on the performance of LLMs cannot be overlooked.Therefore,we propose an FDI attack detection and LLM-assisted resource allocation algorithm for 6G edge intelligenceempowered distribution power grids.First,we formulate a resource allocation optimization problem.The objective is to minimize the weighted sum of the global loss function and total LLM fine-tuning delay under constraints of long-term privacy entropy and energy consumption.Then,we decouple it based on virtual queues.We utilize an LLM-assisted deep Q network(DQN)to learn the resource allocation strategy and design an FDI attack detection mechanism to ensure that fine-tuning remains on the correct path.Simulations demonstrate that the proposed algorithm has excellent performance in convergence,delay,and security.展开更多
As the density of wireless networks increases globally, the vulnerability of overlapped dense wireless communications to interference by hidden nodes and denial-of-service (DoS) attacks is becoming more apparent. Ther...As the density of wireless networks increases globally, the vulnerability of overlapped dense wireless communications to interference by hidden nodes and denial-of-service (DoS) attacks is becoming more apparent. There exists a gap in research on the detection and response to attacks on Medium Access Control (MAC) mechanisms themselves, which would lead to service outages between nodes. Classifying exploitation and deceptive jamming attacks on control mechanisms is particularly challengingdue to their resemblance to normal heavy communication patterns. Accordingly, this paper proposes a machine learning-based selective attack mitigation model that detects DoS attacks on wireless networks by monitoring packet log data. Based on the type of detected attack, it implements effective corresponding mitigation techniques to restore performance to nodes whose availability has been compromised. Experimental results reveal that the accuracy of the proposed model is 14% higher than that of a baseline anomaly detection model. Further, the appropriate mitigation techniques selected by the proposed system based on the attack type improve the average throughput by more than 440% compared to the case without a response.展开更多
基金funded by the Deanship of Scientific Research(DSR)at King Abdulaziz University,Jeddah,under Grant No.(GPIP:1074-612-2024).
文摘The surge in smishing attacks underscores the urgent need for robust,real-time detection systems powered by advanced deep learning models.This paper introduces PhishNet,a novel ensemble learning framework that integrates transformer-based models(RoBERTa)and large language models(LLMs)(GPT-OSS 120B,LLaMA3.370B,and Qwen332B)to enhance smishing detection performance significantly.To mitigate class imbalance,we apply synthetic data augmentation using T5 and leverage various text preprocessing techniques.Our system employs a duallayer voting mechanism:weighted majority voting among LLMs and a final ensemble vote to classify messages as ham,spam,or smishing.Experimental results show an average accuracy improvement from 96%to 98.5%compared to the best standalone transformer,and from 93%to 98.5%when compared to LLMs across datasets.Furthermore,we present a real-time,user-friendly application to operationalize our detection model for practical use.PhishNet demonstrates superior scalability,usability,and detection accuracy,filling critical gaps in current smishing detection methodologies.
基金funded by the National Key Research and Development Program of China(Grant No.2024YFE0209000)the NSFC(Grant No.U23B2019).
文摘Graph Neural Networks(GNNs)have proven highly effective for graph classification across diverse fields such as social networks,bioinformatics,and finance,due to their capability to learn complex graph structures.However,despite their success,GNNs remain vulnerable to adversarial attacks that can significantly degrade their classification accuracy.Existing adversarial attack strategies primarily rely on label information to guide the attacks,which limits their applicability in scenarios where such information is scarce or unavailable.This paper introduces an innovative unsupervised attack method for graph classification,which operates without relying on label information,thereby enhancing its applicability in a broad range of scenarios.Specifically,our method first leverages a graph contrastive learning loss to learn high-quality graph embeddings by comparing different stochastic augmented views of the graphs.To effectively perturb the graphs,we then introduce an implicit estimator that measures the impact of various modifications on graph structures.The proposed strategy identifies and flips edges with the top-K highest scores,determined by the estimator,to maximize the degradation of the model’s performance.In addition,to defend against such attack,we propose a lightweight regularization-based defense mechanism that is specifically tailored to mitigate the structural perturbations introduced by our attack strategy.It enhances model robustness by enforcing embedding consistency and edge-level smoothness during training.We conduct experiments on six public TU graph classification datasets:NCI1,NCI109,Mutagenicity,ENZYMES,COLLAB,and DBLP_v1,to evaluate the effectiveness of our attack and defense strategies.Under an attack budget of 3,the maximum reduction in model accuracy reaches 6.67%on the Graph Convolutional Network(GCN)and 11.67%on the Graph Attention Network(GAT)across different datasets,indicating that our unsupervised method induces degradation comparable to state-of-the-art supervised attacks.Meanwhile,our defense achieves the highest accuracy recovery of 3.89%(GCN)and 5.00%(GAT),demonstrating improved robustness against structural perturbations.
文摘Zero-click attacks represent an advanced cybersecurity threat,capable of compromising devices without user interaction.High-profile examples such as Pegasus,Simjacker,Bluebugging,and Bluesnarfing exploit hidden vulnerabilities in software and communication protocols to silently gain access,exfiltrate data,and enable long-term surveillance.Their stealth and ability to evade traditional defenses make detection and mitigation highly challenging.This paper addresses these threats by systematically mapping the tactics and techniques of zero-click attacks using the MITRE ATT&CK framework,a widely adopted standard for modeling adversarial behavior.Through this mapping,we categorize real-world attack vectors and better understand how such attacks operate across the cyber-kill chain.To support threat detection efforts,we propose an Active Learning-based method to efficiently label the Pegasus spyware dataset in alignment with the MITRE ATT&CK framework.This approach reduces the effort of manually annotating data while improving the quality of the labeled data,which is essential to train robust cybersecurity models.In addition,our analysis highlights the structured execution paths of zero-click attacks and reveals gaps in current defense strategies.The findings emphasize the importance of forward-looking strategies such as continuous surveillance,dynamic threat profiling,and security education.By bridging zero-click attack analysis with the MITRE ATT&CK framework and leveraging machine learning for dataset annotation,this work provides a foundation for more accurate threat detection and the development of more resilient and structured cybersecurity frameworks.
基金supported by Key Laboratory of Cyberspace Security,Ministry of Education,China。
文摘Transformer-based models have significantly advanced binary code similarity detection(BCSD)by leveraging their semantic encoding capabilities for efficient function matching across diverse compilation settings.Although adversarial examples can strategically undermine the accuracy of BCSD models and protect critical code,existing techniques predominantly depend on inserting artificial instructions,which incur high computational costs and offer limited diversity of perturbations.To address these limitations,we propose AIMA,a novel gradient-guided assembly instruction relocation method.Our method decouples the detection model into tokenization,embedding,and encoding layers to enable efficient gradient computation.Since token IDs of instructions are discrete and nondifferentiable,we compute gradients in the continuous embedding space to evaluate the influence of each token.The most critical tokens are identified by calculating the L2 norm of their embedding gradients.We then establish a mapping between instructions and their corresponding tokens to aggregate token-level importance into instructionlevel significance.To maximize adversarial impact,a sliding window algorithm selects the most influential contiguous segments for relocation,ensuring optimal perturbation with minimal length.This approach efficiently locates critical code regions without expensive search operations.The selected segments are relocated outside their original function boundaries via a jump mechanism,which preserves runtime control flow and functionality while introducing“deletion”effects in the static instruction sequence.Extensive experiments show that AIMA reduces similarity scores by up to 35.8%in state-of-the-art BCSD models.When incorporated into training data,it also enhances model robustness,achieving a 5.9%improvement in AUROC.
基金supported by the Institute of Information&Communications Technology Planning&Evaluation(IITP)grant funded by the Korea government(MSIT)(No.RS-2023-00235509Development of security monitoring technology based network behavior against encrypted cyber threats in ICT convergence environment).
文摘With the increasing emphasis on personal information protection,encryption through security protocols has emerged as a critical requirement in data transmission and reception processes.Nevertheless,IoT ecosystems comprise heterogeneous networks where outdated systems coexist with the latest devices,spanning a range of devices from non-encrypted ones to fully encrypted ones.Given the limited visibility into payloads in this context,this study investigates AI-based attack detection methods that leverage encrypted traffic metadata,eliminating the need for decryption and minimizing system performance degradation—especially in light of these heterogeneous devices.Using the UNSW-NB15 and CICIoT-2023 dataset,encrypted and unencrypted traffic were categorized according to security protocol,and AI-based intrusion detection experiments were conducted for each traffic type based on metadata.To mitigate the problem of class imbalance,eight different data sampling techniques were applied.The effectiveness of these sampling techniques was then comparatively analyzed using two ensemble models and three Deep Learning(DL)models from various perspectives.The experimental results confirmed that metadata-based attack detection is feasible using only encrypted traffic.In the UNSW-NB15 dataset,the f1-score of encrypted traffic was approximately 0.98,which is 4.3%higher than that of unencrypted traffic(approximately 0.94).In addition,analysis of the encrypted traffic in the CICIoT-2023 dataset using the same method showed a significantly lower f1-score of roughly 0.43,indicating that the quality of the dataset and the preprocessing approach have a substantial impact on detection performance.Furthermore,when data sampling techniques were applied to encrypted traffic,the recall in the UNSWNB15(Encrypted)dataset improved by up to 23.0%,and in the CICIoT-2023(Encrypted)dataset by 20.26%,showing a similar level of improvement.Notably,in CICIoT-2023,f1-score and Receiver Operation Characteristic-Area Under the Curve(ROC-AUC)increased by 59.0%and 55.94%,respectively.These results suggest that data sampling can have a positive effect even in encrypted environments.However,the extent of the improvement may vary depending on data quality,model architecture,and sampling strategy.
基金supported by Princess Nourah bint Abdulrahman University Researchers Supporting Project Number(PNURSP2025R97)Princess Nourah bint Abdulrahman University,Riyadh,Saudi Arabia.
文摘The exponential growth of the Internet of Things(IoT)has introduced significant security challenges,with zero-day attacks emerging as one of the most critical and challenging threats.Traditional Machine Learning(ML)and Deep Learning(DL)techniques have demonstrated promising early detection capabilities.However,their effectiveness is limited when handling the vast volumes of IoT-generated data due to scalability constraints,high computational costs,and the costly time-intensive process of data labeling.To address these challenges,this study proposes a Federated Learning(FL)framework that leverages collaborative and hybrid supervised learning to enhance cyber threat detection in IoT networks.By employing Deep Neural Networks(DNNs)and decentralized model training,the approach reduces computational complexity while improving detection accuracy.The proposed model demonstrates robust performance,achieving accuracies of 94.34%,99.95%,and 87.94%on the publicly available kitsune,Bot-IoT,and UNSW-NB15 datasets,respectively.Furthermore,its ability to detect zero-day attacks is validated through evaluations on two additional benchmark datasets,TON-IoT and IoT-23,using a Deep Federated Learning(DFL)framework,underscoring the generalization and effectiveness of the model in heterogeneous and decentralized IoT environments.Experimental results demonstrate superior performance over existing methods,establishing the proposed framework as an efficient and scalable solution for IoT security.
基金National Natural Science Foundation of China(62272147,12471492,62072161,12401687)Shandong Provincial Natural Science Foundation(ZR2024QA205)+1 种基金Science and Technology on Communication Security Laboratory Foundation(6142103012207)Innovation Group Project of the Natural Science Foundation of Hubei Province of China(2023AFA021)。
文摘Ballet is one of the finalists of the block cipher project in the 2019 National Cryptographic Algorithm Design Competition.This study aims to conduct a comprehensive security evaluation of Ballet from the perspective of differential-linear(DL)cryptanalysis.Specifically,we present an automated search for the DL distinguishers of Ballet based on MILP/MIQCP.For the versions with block sizes of 128 and 256 bits,we obtain 16 and 22 rounds distinguishers with estimated correlations of 2^(-59.89)and 2^(-116.80),both of which are the publicly longest distinguishers.In addition,this study incorporates the complexity information of key-recovery attacks into the automated model,to search for the optimal key-recovery attack structures based on DL distinguishers.As a result,we mount the key-recovery attacks on 16-round Ballet-128/128,17-round Ballet-128/256,and 21-round Ballet-256/256.The data/time complexities for these attacks are 2^(108.36)/2^(120.36),2^(115.90)/2^(192),and 2^(227.62)/2^(240.67),respectively.
基金supported by the Foundation of Science and Technology on Information Assurance Laboratory(No.KJ-17-003)
文摘Asymmetric cryptographic schemes, represe nted by RSA, have bee n show n to be in secure un der quantum computing conditions. Correspondingly, there is a need to study whether the symmetric cryptosystem can still guarantee high security with the advent of quantum computers. In this paper, based on the basic principles of classical slide attacks and Simon's algorithm, we take LED-like lightweight block ciphers as research objects to present a security analysis under both classical and quantum attacks, fully considering the influence on the security of the ciphers of adding the round constants. By analyzing the information leakage of round constants, we can introduce the differential of the round constants to propose a classical slide attack on full-round LED-64 with a probability of 1. The analysis result shows that LED-64 is unable to resist this kind of classical slide attack, but that attack method is not applicable to LED-128. As for quantum attacks, by improving on existing quantum attack methods we dem on strate a qua ntum single-key slide attack on LED-64 and a quantum related-key attack on LED- 128, and indicators of the two attack algorithms are analyzed in detail. The attack results show that adding round consta nts does not completely improve the security of the ciphers, and quantum attacks can provide an exp on ential speed-up over the same attacks in the classical model. It further illustrates that the block cipher that is proved to be safe under classical settings is not necessarily secure under quantum conditions.
文摘In EUROCRYPT 2017,a new structure-difference property,say“a-multiple-of-8”was proposed on 5-round AES.Inspired by the idea,yoyo attacks and mixture differential attacks were proposed yielding new records on data and computational complexities for key-recovery attacks against 5-round AES.In this paper,the authors attempt to apply the idea of mixture differential cryptanalysis to Midori64.Midori is a lightweight block cipher proposed at ASIACRYPT 2015.Although the structure of Midori is similar to AES,the MixColumn matrix of Midori is not MDS.Based on this observation,the authors present a class of deterministic differential trails on 2-round Midori.Then combined with the yoyo trick,a new type of 4-round retracing boomerang distinguishers is obtained on Midori.Based on the new 4-round distinguishers,a key-recovery attack on 6-round Midori64 is given that requires only 2^(27)computational complexity,2^(29)chosen plaintexts,2^(20)adaptively chosen ciphertexts.The key-recovery attack has been experimentally verified.
基金supported by National Key Research and Development Program of China under Grant No.2018YFA0704705the National Natural Science Foundation of China under Grant Nos. 62032009, 12201193+3 种基金12226006the Innovation Program for Quantum Science and Technology under Grant No. 2021ZD0302902the Innovation Group Project of the Natural Science Foundation of Hubei Province of China under Grant No.2023AFA021the Science and Technology Research Program of Education Department of Hubei Province under Grant No. Q20221008。
文摘In ASIACCS 2015, Nu nez, et al. proposed a proxy re-encryption scheme, named NTRURe Encrypt, based on NTRU, which allows a proxy to translate ciphertext under the delegator’s public key into a re-encrypted ciphertext that can be decrypted correctly by delegatee’s private key. Because of the potential resistance to quantum algorithm, high efficiency and various applications in real life,NTRURe Encrypt has drawn lots of attention and its security has been widely discussed and analyzed.In PQCrypto2019, Liu, et al. proposed two key recovery attacks against it. However, their first attack heavily relies on a weaken decryption oracle, and the second attack needs to collect about 260ciphertexts from the same message by theoretical analysis, which makes both of the attacks unrealistic. In this paper, inspired by the broadcast attack against NTRU, the authors find out that for NTRURe Encrypt the delegator and the delegatee can efficiently recover each other’s private key in polynomial time without any unrealistic assumptions. In addition, the authors also show how to fix NTRURe Encrypt to resist the proposed attacks. As a by-product, the authors also show how to commit broadcast attacks against NTRU 2001 with even dg, which was thought infeasible before.
基金The National Natural Science Foundation of China(W2431048)The Science and Technology Research Program of Chongqing Municipal Education Commission,China(KJZDK202300807)The Chongqing Natural Science Foundation,China(CSTB2024NSCQQCXMX0052).
文摘This paper addresses the consensus problem of nonlinear multi-agent systems subject to external disturbances and uncertainties under denial-ofservice(DoS)attacks.Firstly,an observer-based state feedback control method is employed to achieve secure control by estimating the system's state in real time.Secondly,by combining a memory-based adaptive eventtriggered mechanism with neural networks,the paper aims to approximate the nonlinear terms in the networked system and efficiently conserve system resources.Finally,based on a two-degree-of-freedom model of a vehicle affected by crosswinds,this paper constructs a multi-unmanned ground vehicle(Multi-UGV)system to validate the effectiveness of the proposed method.Simulation results show that the proposed control strategy can effectively handle external disturbances such as crosswinds in practical applications,ensuring the stability and reliable operation of the Multi-UGV system.
文摘Watermarking is embedding visible or invisible data within media to verify its authenticity or protect copyright.The watermark is embedded in significant spatial or frequency features of the media to make it more resistant to intentional or unintentional modification.Some of these features are important perceptual features according to the human visual system(HVS),which means that the embedded watermark should be imperceptible in these features.Therefore,both the designers of watermarking algorithms and potential attackers must consider these perceptual features when carrying out their actions.The two roles will be considered in this paper when designing a robust watermarking algorithm against the most harmful attacks,like volumetric scaling,histogram equalization,and non-conventional watermarking attacks like the Denoising Convolution Neural Network(DnCNN),which must be considered in watermarking algorithm design due to its rising role in the state-of-the-art attacks.The DnCNN is initialized and trained using watermarked image samples created by our proposed Covert and Severe Attacks Resistant Watermarking Algorithm(CSRWA)to prove its robustness.For this algorithm to satisfy the robustness and imperceptibility tradeoff,implementing the Dither Modulation(DM)algorithm is boosted by utilizing the Just Noticeable Distortion(JND)principle to get an improved performance in this sense.Sensitivity,luminance,inter and intra-block contrast are used to adjust the JND values.
基金supported by Jiangsu Provincial Science and Technology Project,grant number J2023124.Jing Guo received this grant,the URLs of sponsors’website is https://kxjst.jiangsu.gov.cn/(accessed on 06 June 2024).
文摘The rapid proliferation of electric vehicle(EV)charging infrastructure introduces critical cybersecurity vulnerabilities to power grids system.This study presents an innovative anomaly detection framework for EV charging stations,addressing the unique challenges posed by third-party aggregation platforms.Our approach integrates node equations-based on the parameter identification with a novel deep learning model,xDeepCIN,to detect abnormal data reporting indicative of aggregation attacks.We employ a graph-theoretic approach to model EV charging networks and utilize Markov Chain Monte Carlo techniques for accurate parameter estimation.The xDeepCIN model,incorporating a Compressed Interaction Network,has the ability to capture complex feature interactions in sparse,high-dimensional charging data.Experimental results on both proprietary and public datasets demonstrate significant improvements in anomaly detection performance,with F1-scores increasing by up to 32.3%for specific anomaly types compared to traditional methods,such as wide&deep and DeepFM(Factorization-Machine).Our framework exhibits robust scalability,effectively handling networks ranging from 8 to 85 charging points.Furthermore,we achieve real-time monitoring capabilities,with parameter identification completing within seconds for networks up to 1000 nodes.This research contributes to enhancing the security and reliability of renewable energy systems against evolving cyber threats,offering a comprehensive solution for safeguarding the rapidly expanding EV charging infrastructure.
基金National Natural Science Foundation of China(Nos.42171130 and 42301158)Pilot Project of China’s Strength in Transportation for the Central Research Institute(No.QG2021-1-4-7)National Key Technology Research and Development Program of the Ministry of Science and Technology of China(No.2021YFB2601200).
文摘Sulfate attack-induced expansion of cement-treated aggregates in seasonally frozen regions is a well-known issue which causes continuous expansion in railway subgrades,and particularly in high-speed railways.Accordingly,we investigated the influence of material proportions,the number of freeze-thaw(FT)cycles,and temperature gradients on the expansion mechanism of sulfate attack on cement-treated aggregates subjected to FT cycles.The conditions,laws,and dominant factors causing the expansion of aggregates were analyzed through swelling tests.The results indicate that under FT cycles,3%content cement-treated graded macadam only experiences slight deformation.The maximum strain of graded macadam attacked by 1%sodium sulfate content in each FT cycle is significantly larger than that of 3%content cement-treated graded macadam attacked by 1%sodium sulfate content.Using scanning electron microscopy,needle-like crystals were observed during sulfate attack of cement-treated graded macadam.Through quantitative analysis,we determined the recoverable and unrecoverable deformations of graded macadam under FT cycles.For graded macadam under sulfate attack,the expansion is mainly induced by periodic frost heave and salt expansion,as well as salt migration.For cement-treated graded macadam under sulfate attack,the expansion is mainly induced by chemical attack and salt migration.This study can serve as a reference for future research on the mechanics of sulfate attack on cement-treated aggregates that experience FT cycles,and provide theoretical support for methods that remediate the expansion induced by sulfate attack.
基金supported by the National Natural Science Foundation of China(Nos.12172315,12072304,11702232)the Fujian Provincial Natural Science Foundation,China(No.2021J01050)the Aeronautical Science Foundation of China(No.20220013068002).
文摘Unsteady aerodynamic characteristics at high angles of attack are of great importance to the design and development of advanced fighter aircraft, which are characterized by post-stall maneuverability with multiple Degrees-of-Freedom(multi-DOF) and complex flow field structure.In this paper, a special kind of cable-driven parallel mechanism is firstly utilized as a new suspension method to conduct unsteady dynamic wind tunnel tests at high angles of attack, thereby providing experimental aerodynamic data. These tests include a wide range of multi-DOF coupled oscillatory motions with various amplitudes and frequencies. Then, for aerodynamic modeling and analysis, a novel data-driven Feature-Level Attention Recurrent neural network(FLAR) is proposed. This model incorporates a specially designed feature-level attention module that focuses on the state variables affecting the aerodynamic coefficients, thereby enhancing the physical interpretability of the aerodynamic model. Subsequently, spin maneuver simulations, using a mathematical model as the baseline, are conducted to validate the effectiveness of the FLAR. Finally, the results on wind tunnel data reveal that the FLAR accurately predicts aerodynamic coefficients, and observations through the visualization of attention scores identify the key state variables that affect the aerodynamic coefficients. It is concluded that the proposed FLAR enhances the interpretability of the aerodynamic model while achieving good prediction accuracy and generalization capability for multi-DOF coupling motion at high angles of attack.
基金Funded by Chinese National Natural Science Foundation of China(No.U2006224)。
文摘The paper presents experimental investigation results of crack pattern change in cement pastes caused by external sulfate attack(ESA).To visualize the formation and development of cracks in cement pastes under ESA,an X-ray computed tomography(X-ray CT)was used,i e,the tomography system of Zeiss Xradia 510 versa.The results indicate that X-CT can monitor the development process and distribution characteristics of the internal cracks of cement pastes under ESA with attack time.In addition,the C3A content in the cement significantly affects the damage mode of cement paste specimens during sulfate erosion.The damage of ordinary Portland cement(OPC)pastes subjected to sulfate attack with high C3A content are severe,while the damage of sulfate resistant Portland cement(SRPC)pastes is much smaller than that of OPC pastes.Furthermore,a quadratic function describes the correlation between the crack volume fraction and development depth for two cement pastes immermed in sulfate solution.
文摘To improve the vertical axis wind turbine(VAWT)design,the angle of attack(AOA)and airfoil data must be treated correctly.The present paper develops a method for determining AOA on a VAWT based on computational fluid dynamics(CFD)analysis.First,a CFD analysis of a two-bladed VAWT equipped with a NACA 0012 airfoil is conducted.The thrust and power coefficients are validated through experiments.Second,the blade force and velocity data at monitoring points are collected.The AOA at different azimuth angles is determined by removing the blade self-induction at the monitoring point.Then,the lift and drag coefficients as a function of AOA are extracted.Results show that this method is independent of the monitoring points selection located at certain distance to the blades and the extracted dynamic stall hysteresis is more precise than the one with the“usual”method without considering the self-induction from bound vortices.
基金supported by Science and Technology Innovation Programfor Postgraduate Students in IDP Subsidized by Fundamental Research Funds for the Central Universities(Project No.ZY20240335)support of the Research Project of the Key Technology of Malicious Code Detection Based on Data Mining in APT Attack(Project No.2022IT173)the Research Project of the Big Data Sensitive Information Supervision Technology Based on Convolutional Neural Network(Project No.2022011033).
文摘Previous studies have shown that deep learning is very effective in detecting known attacks.However,when facing unknown attacks,models such as Deep Neural Networks(DNN)combined with Long Short-Term Memory(LSTM),Convolutional Neural Networks(CNN)combined with LSTM,and so on are built by simple stacking,which has the problems of feature loss,low efficiency,and low accuracy.Therefore,this paper proposes an autonomous detectionmodel for Distributed Denial of Service attacks,Multi-Scale Convolutional Neural Network-Bidirectional Gated Recurrent Units-Single Headed Attention(MSCNN-BiGRU-SHA),which is based on a Multistrategy Integrated Zebra Optimization Algorithm(MI-ZOA).The model undergoes training and testing with the CICDDoS2019 dataset,and its performance is evaluated on a new GINKS2023 dataset.The hyperparameters for Conv_filter and GRU_unit are optimized using the Multi-strategy Integrated Zebra Optimization Algorithm(MIZOA).The experimental results show that the test accuracy of the MSCNN-BiGRU-SHA model based on the MIZOA proposed in this paper is as high as 0.9971 in the CICDDoS 2019 dataset.The evaluation accuracy of the new dataset GINKS2023 created in this paper is 0.9386.Compared to the MSCNN-BiGRU-SHA model based on the Zebra Optimization Algorithm(ZOA),the detection accuracy on the GINKS2023 dataset has improved by 5.81%,precisionhas increasedby 1.35%,the recallhas improvedby 9%,and theF1scorehas increasedby 5.55%.Compared to the MSCNN-BiGRU-SHA models developed using Grid Search,Random Search,and Bayesian Optimization,the MSCNN-BiGRU-SHA model optimized with the MI-ZOA exhibits better performance in terms of accuracy,precision,recall,and F1 score.
基金supported by the Science and Technology Project of State Grid Corporation of China under Grant Number 52094021N010(5400-202199534A-0-5-ZN).
文摘The intelligent operation management of distribution services is crucial for the stability of power systems.Integrating the large language model(LLM)with 6G edge intelligence provides customized management solutions.However,the adverse effects of false data injection(FDI)attacks on the performance of LLMs cannot be overlooked.Therefore,we propose an FDI attack detection and LLM-assisted resource allocation algorithm for 6G edge intelligenceempowered distribution power grids.First,we formulate a resource allocation optimization problem.The objective is to minimize the weighted sum of the global loss function and total LLM fine-tuning delay under constraints of long-term privacy entropy and energy consumption.Then,we decouple it based on virtual queues.We utilize an LLM-assisted deep Q network(DQN)to learn the resource allocation strategy and design an FDI attack detection mechanism to ensure that fine-tuning remains on the correct path.Simulations demonstrate that the proposed algorithm has excellent performance in convergence,delay,and security.
基金supported by the Ministry of Trade,Industry and Energy(MOTIE)under Training Industrial Security Specialist for High-Tech Industry(RS-2024-00415520)supervised by the Korea Institute for Advancement of Technology(KIAT)the Ministry of Science and ICT(MSIT)under the ICT Challenge and Advanced Network of HRD(ICAN)Program(No.IITP-2022-RS-2022-00156310)supervised by the Institute of Information&Communication Technology Planning&Evaluation(IITP).
文摘As the density of wireless networks increases globally, the vulnerability of overlapped dense wireless communications to interference by hidden nodes and denial-of-service (DoS) attacks is becoming more apparent. There exists a gap in research on the detection and response to attacks on Medium Access Control (MAC) mechanisms themselves, which would lead to service outages between nodes. Classifying exploitation and deceptive jamming attacks on control mechanisms is particularly challengingdue to their resemblance to normal heavy communication patterns. Accordingly, this paper proposes a machine learning-based selective attack mitigation model that detects DoS attacks on wireless networks by monitoring packet log data. Based on the type of detected attack, it implements effective corresponding mitigation techniques to restore performance to nodes whose availability has been compromised. Experimental results reveal that the accuracy of the proposed model is 14% higher than that of a baseline anomaly detection model. Further, the appropriate mitigation techniques selected by the proposed system based on the attack type improve the average throughput by more than 440% compared to the case without a response.
