In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mec...In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mechanisms during aggregation,it is difficult to conduct effective backdoor attacks.In addition,existing backdoor attack methods are faced with challenges,such as low backdoor accuracy,poor ability to evade anomaly detection,and unstable model training.To address these challenges,a method called adaptive simulation backdoor attack(ASBA)is proposed.Specifically,ASBA improves the stability of model training by manipulating the local training process and using an adaptive mechanism,the ability of the malicious model to evade anomaly detection by combing large simulation training and clipping,and the backdoor accuracy by introducing a stimulus model to amplify the impact of the backdoor in the global model.Extensive comparative experiments under five advanced defense scenarios show that ASBA can effectively evade anomaly detection and achieve high backdoor accuracy in the global model.Furthermore,it exhibits excellent stability and effectiveness after multiple rounds of attacks,outperforming state-of-the-art backdoor attack methods.展开更多
Federated Learning(FL)protects data privacy through a distributed training mechanism,yet its decentralized nature also introduces new security vulnerabilities.Backdoor attacks inject malicious triggers into the global...Federated Learning(FL)protects data privacy through a distributed training mechanism,yet its decentralized nature also introduces new security vulnerabilities.Backdoor attacks inject malicious triggers into the global model through compromised updates,posing significant threats to model integrity and becoming a key focus in FL security.Existing backdoor attack methods typically embed triggers directly into original images and consider only data heterogeneity,resulting in limited stealth and adaptability.To address the heterogeneity of malicious client devices,this paper proposes a novel backdoor attack method named Capability-Adaptive Shadow Backdoor Attack(CASBA).By incorporating measurements of clients’computational and communication capabilities,CASBA employs a dynamic hierarchical attack strategy that adaptively aligns attack intensity with available resources.Furthermore,an improved deep convolutional generative adversarial network(DCGAN)is integrated into the attack pipeline to embed triggers without modifying original data,significantly enhancing stealthiness.Comparative experiments with Shadow Backdoor Attack(SBA)across multiple scenarios demonstrate that CASBA dynamically adjusts resource consumption based on device capabilities,reducing average memory usage per iteration by 5.8%.CASBA improves resource efficiency while keeping the drop in attack success rate within 3%.Additionally,the effectiveness of CASBA against three robust FL algorithms is also validated.展开更多
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
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
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
In recent years,with the rapid advancement of artificial intelligence,object detection algorithms have made significant strides in accuracy and computational efficiency.Notably,research and applications of Anchor-Free...In recent years,with the rapid advancement of artificial intelligence,object detection algorithms have made significant strides in accuracy and computational efficiency.Notably,research and applications of Anchor-Free models have opened new avenues for real-time target detection in optical remote sensing images(ORSIs).However,in the realmof adversarial attacks,developing adversarial techniques tailored to Anchor-Freemodels remains challenging.Adversarial examples generated based on Anchor-Based models often exhibit poor transferability to these new model architectures.Furthermore,the growing diversity of Anchor-Free models poses additional hurdles to achieving robust transferability of adversarial attacks.This study presents an improved cross-conv-block feature fusion You Only Look Once(YOLO)architecture,meticulously engineered to facilitate the extraction ofmore comprehensive semantic features during the backpropagation process.To address the asymmetry between densely distributed objects in ORSIs and the corresponding detector outputs,a novel dense bounding box attack strategy is proposed.This approach leverages dense target bounding boxes loss in the calculation of adversarial loss functions.Furthermore,by integrating translation-invariant(TI)and momentum-iteration(MI)adversarial methodologies,the proposed framework significantly improves the transferability of adversarial attacks.Experimental results demonstrate that our method achieves superior adversarial attack performance,with adversarial transferability rates(ATR)of 67.53%on the NWPU VHR-10 dataset and 90.71%on the HRSC2016 dataset.Compared to ensemble adversarial attack and cascaded adversarial attack approaches,our method generates adversarial examples in an average of 0.64 s,representing an approximately 14.5%improvement in efficiency under equivalent conditions.展开更多
Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that man...Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.展开更多
Internet of Things(IoTs)devices are bringing about a revolutionary change our society by enabling connectivity regardless of time and location.However,The extensive deployment of these devices also makes them attracti...Internet of Things(IoTs)devices are bringing about a revolutionary change our society by enabling connectivity regardless of time and location.However,The extensive deployment of these devices also makes them attractive victims for themalicious actions of adversaries.Within the spectrumof existing threats,Side-ChannelAttacks(SCAs)have established themselves as an effective way to compromise cryptographic implementations.These attacks exploit unintended,unintended physical leakage that occurs during the cryptographic execution of devices,bypassing the theoretical strength of the crypto design.In recent times,the advancement of deep learning has provided SCAs with a powerful ally.Well-trained deep-learningmodels demonstrate an exceptional capacity to identify correlations between side-channel measurements and sensitive data,thereby significantly enhancing such attacks.To further understand the security threats posed by deep-learning SCAs and to aid in formulating robust countermeasures in the future,this paper undertakes an exhaustive investigation of leading-edge SCAs targeting Advanced Encryption Standard(AES)implementations.The study specifically focuses on attacks that exploit power consumption and electromagnetic(EM)emissions as primary leakage sources,systematically evaluating the extent to which diverse deep learning techniques enhance SCAs acrossmultiple critical dimensions.These dimensions include:(i)the characteristics of publicly available datasets derived from various hardware and software platforms;(ii)the formalization of leakage models tailored to different attack scenarios;(iii)the architectural suitability and performance of state-of-the-art deep learning models.Furthermore,the survey provides a systematic synthesis of current research findings,identifies significant unresolved issues in the existing literature and suggests promising directions for future work,including cross-device attack transferability and the impact of quantum-classical hybrid computing on side-channel security.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 increasing intelligence of power systems is transforming distribution networks into Cyber-Physical Distribution Systems(CPDS).While enabling advanced functionalities,the tight interdependence between cyber and phy...The increasing intelligence of power systems is transforming distribution networks into Cyber-Physical Distribution Systems(CPDS).While enabling advanced functionalities,the tight interdependence between cyber and physical layers introduces significant security challenges and amplifies operational risks.To address these critical issues,this paper proposes a comprehensive risk assessment framework that explicitly incorporates the physical dependence of information systems.A Bayesian attack graph is employed to quantitatively evaluate the likelihood of successful cyber attacks.By analyzing the critical scenario of fault current path misjudgment,we define novel system-level and node-level risk coupling indices to preciselymeasure the cascading impacts across cyber and physical domains.Furthermore,an attack-responsive power recovery optimization model is established,integrating DistFlowbased physical constraints and sophisticated modeling of information-dependent interference.To enhance resilience against varying attack scenarios,a defense resource allocation model is constructed,where the complex Mixed-Integer Nonlinear Programming(MINLP)problem is efficiently linearized into a Mixed-Integer Linear Programming(MILP)formulation.Finally,to mitigate the impact of targeted attacks,the optimal deployment of terminal defense resources is determined using a Stackelberg game-theoretic approach,aiming to minimize overall system risk.The robustness and effectiveness of the proposed integrated framework are rigorously validated through extensive simulations under diverse attack intensities and defense resource constraints.展开更多
Optimizing convolutional neural networks(CNNs)for IoT attack detection remains a critical yet challenging task due to the need to balance multiple performance metrics beyond mere accuracy.This study proposes a unified...Optimizing convolutional neural networks(CNNs)for IoT attack detection remains a critical yet challenging task due to the need to balance multiple performance metrics beyond mere accuracy.This study proposes a unified and flexible optimization framework that leverages metaheuristic algorithms to automatically optimize CNN configurations for IoT attack detection.Unlike conventional single-objective approaches,the proposed method formulates a global multi-objective fitness function that integrates accuracy,precision,recall,and model size(speed/model complexity penalty)with adjustable weights.This design enables both single-objective and weightedsum multi-objective optimization,allowing adaptive selection of optimal CNN configurations for diverse deployment requirements.Two representativemetaheuristic algorithms,GeneticAlgorithm(GA)and Particle Swarm Optimization(PSO),are employed to optimize CNNhyperparameters and structure.At each generation/iteration,the best configuration is selected as themost balanced solution across optimization objectives,i.e.,the one achieving themaximum value of the global objective function.Experimental validation on two benchmark datasets,Edge-IIoT and CIC-IoT2023,demonstrates that the proposed GA-and PSO-based models significantly enhance detection accuracy(94.8%–98.3%)and generalization compared with manually tuned CNN configurations,while maintaining compact architectures.The results confirm that the multi-objective framework effectively balances predictive performance and computational efficiency.This work establishes a generalizable and adaptive optimization strategy for deep learning-based IoT attack detection and provides a foundation for future hybrid metaheuristic extensions in broader IoT security applications.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
文摘In federated learning,backdoor attacks have become an important research topic with their wide application in processing sensitive datasets.Since federated learning detects or modifies local models through defense mechanisms during aggregation,it is difficult to conduct effective backdoor attacks.In addition,existing backdoor attack methods are faced with challenges,such as low backdoor accuracy,poor ability to evade anomaly detection,and unstable model training.To address these challenges,a method called adaptive simulation backdoor attack(ASBA)is proposed.Specifically,ASBA improves the stability of model training by manipulating the local training process and using an adaptive mechanism,the ability of the malicious model to evade anomaly detection by combing large simulation training and clipping,and the backdoor accuracy by introducing a stimulus model to amplify the impact of the backdoor in the global model.Extensive comparative experiments under five advanced defense scenarios show that ASBA can effectively evade anomaly detection and achieve high backdoor accuracy in the global model.Furthermore,it exhibits excellent stability and effectiveness after multiple rounds of attacks,outperforming state-of-the-art backdoor attack methods.
基金supported by the National Natural Science Foundation of China(Grant No.62172123)the Key Research and Development Program of Heilongjiang Province,China(GrantNo.2022ZX01A36).
文摘Federated Learning(FL)protects data privacy through a distributed training mechanism,yet its decentralized nature also introduces new security vulnerabilities.Backdoor attacks inject malicious triggers into the global model through compromised updates,posing significant threats to model integrity and becoming a key focus in FL security.Existing backdoor attack methods typically embed triggers directly into original images and consider only data heterogeneity,resulting in limited stealth and adaptability.To address the heterogeneity of malicious client devices,this paper proposes a novel backdoor attack method named Capability-Adaptive Shadow Backdoor Attack(CASBA).By incorporating measurements of clients’computational and communication capabilities,CASBA employs a dynamic hierarchical attack strategy that adaptively aligns attack intensity with available resources.Furthermore,an improved deep convolutional generative adversarial network(DCGAN)is integrated into the attack pipeline to embed triggers without modifying original data,significantly enhancing stealthiness.Comparative experiments with Shadow Backdoor Attack(SBA)across multiple scenarios demonstrate that CASBA dynamically adjusts resource consumption based on device capabilities,reducing average memory usage per iteration by 5.8%.CASBA improves resource efficiency while keeping the drop in attack success rate within 3%.Additionally,the effectiveness of CASBA against three robust FL algorithms is also validated.
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.
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In recent years,with the rapid advancement of artificial intelligence,object detection algorithms have made significant strides in accuracy and computational efficiency.Notably,research and applications of Anchor-Free models have opened new avenues for real-time target detection in optical remote sensing images(ORSIs).However,in the realmof adversarial attacks,developing adversarial techniques tailored to Anchor-Freemodels remains challenging.Adversarial examples generated based on Anchor-Based models often exhibit poor transferability to these new model architectures.Furthermore,the growing diversity of Anchor-Free models poses additional hurdles to achieving robust transferability of adversarial attacks.This study presents an improved cross-conv-block feature fusion You Only Look Once(YOLO)architecture,meticulously engineered to facilitate the extraction ofmore comprehensive semantic features during the backpropagation process.To address the asymmetry between densely distributed objects in ORSIs and the corresponding detector outputs,a novel dense bounding box attack strategy is proposed.This approach leverages dense target bounding boxes loss in the calculation of adversarial loss functions.Furthermore,by integrating translation-invariant(TI)and momentum-iteration(MI)adversarial methodologies,the proposed framework significantly improves the transferability of adversarial attacks.Experimental results demonstrate that our method achieves superior adversarial attack performance,with adversarial transferability rates(ATR)of 67.53%on the NWPU VHR-10 dataset and 90.71%on the HRSC2016 dataset.Compared to ensemble adversarial attack and cascaded adversarial attack approaches,our method generates adversarial examples in an average of 0.64 s,representing an approximately 14.5%improvement in efficiency under equivalent conditions.
基金supported by 2023 Higher Education Scientific Research Planning Project of China Society of Higher Education(No.23PG0408)2023 Philosophy and Social Science Research Programs in Jiangsu Province(No.2023SJSZ0993)+2 种基金Nantong Science and Technology Project(No.JC2023070)Key Project of Jiangsu Province Education Science 14th Five-Year Plan(Grant No.B-b/2024/02/41)the Open Fund of Advanced Cryptography and System Security Key Laboratory of Sichuan Province(Grant No.SKLACSS-202407).
文摘Large language models(LLMs)have revolutionized AI applications across diverse domains.However,their widespread deployment has introduced critical security vulnerabilities,particularly prompt injection attacks that manipulate model behavior through malicious instructions.Following Kitchenham’s guidelines,this systematic review synthesizes 128 peer-reviewed studies from 2022 to 2025 to provide a unified understanding of this rapidly evolving threat landscape.Our findings reveal a swift progression from simple direct injections to sophisticated multimodal attacks,achieving over 90%success rates against unprotected systems.In response,defense mechanisms show varying effectiveness:input preprocessing achieves 60%–80%detection rates and advanced architectural defenses demonstrate up to 95%protection against known patterns,though significant gaps persist against novel attack vectors.We identified 37 distinct defense approaches across three categories,but standardized evaluation frameworks remain limited.Our analysis attributes these vulnerabilities to fundamental LLM architectural limitations,such as the inability to distinguish instructions from data and attention mechanism vulnerabilities.This highlights critical research directions such as formal verification methods,standardized evaluation protocols,and architectural innovations for inherently secure LLM designs.
基金The Key R&D Program of Hunan Province(Grant No.2025AQ2024)of the Department of Science and Technology of Hunan Province.Distinguished Young Scientists Fund(Grant No.24B0446)of Hunan Education Department.
文摘Internet of Things(IoTs)devices are bringing about a revolutionary change our society by enabling connectivity regardless of time and location.However,The extensive deployment of these devices also makes them attractive victims for themalicious actions of adversaries.Within the spectrumof existing threats,Side-ChannelAttacks(SCAs)have established themselves as an effective way to compromise cryptographic implementations.These attacks exploit unintended,unintended physical leakage that occurs during the cryptographic execution of devices,bypassing the theoretical strength of the crypto design.In recent times,the advancement of deep learning has provided SCAs with a powerful ally.Well-trained deep-learningmodels demonstrate an exceptional capacity to identify correlations between side-channel measurements and sensitive data,thereby significantly enhancing such attacks.To further understand the security threats posed by deep-learning SCAs and to aid in formulating robust countermeasures in the future,this paper undertakes an exhaustive investigation of leading-edge SCAs targeting Advanced Encryption Standard(AES)implementations.The study specifically focuses on attacks that exploit power consumption and electromagnetic(EM)emissions as primary leakage sources,systematically evaluating the extent to which diverse deep learning techniques enhance SCAs acrossmultiple critical dimensions.These dimensions include:(i)the characteristics of publicly available datasets derived from various hardware and software platforms;(ii)the formalization of leakage models tailored to different attack scenarios;(iii)the architectural suitability and performance of state-of-the-art deep learning models.Furthermore,the survey provides a systematic synthesis of current research findings,identifies significant unresolved issues in the existing literature and suggests promising directions for future work,including cross-device attack transferability and the impact of quantum-classical hybrid computing on side-channel security.
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 China Southern Power Grid Company Limited(066500KK52222006).
文摘The increasing intelligence of power systems is transforming distribution networks into Cyber-Physical Distribution Systems(CPDS).While enabling advanced functionalities,the tight interdependence between cyber and physical layers introduces significant security challenges and amplifies operational risks.To address these critical issues,this paper proposes a comprehensive risk assessment framework that explicitly incorporates the physical dependence of information systems.A Bayesian attack graph is employed to quantitatively evaluate the likelihood of successful cyber attacks.By analyzing the critical scenario of fault current path misjudgment,we define novel system-level and node-level risk coupling indices to preciselymeasure the cascading impacts across cyber and physical domains.Furthermore,an attack-responsive power recovery optimization model is established,integrating DistFlowbased physical constraints and sophisticated modeling of information-dependent interference.To enhance resilience against varying attack scenarios,a defense resource allocation model is constructed,where the complex Mixed-Integer Nonlinear Programming(MINLP)problem is efficiently linearized into a Mixed-Integer Linear Programming(MILP)formulation.Finally,to mitigate the impact of targeted attacks,the optimal deployment of terminal defense resources is determined using a Stackelberg game-theoretic approach,aiming to minimize overall system risk.The robustness and effectiveness of the proposed integrated framework are rigorously validated through extensive simulations under diverse attack intensities and defense resource constraints.
文摘Optimizing convolutional neural networks(CNNs)for IoT attack detection remains a critical yet challenging task due to the need to balance multiple performance metrics beyond mere accuracy.This study proposes a unified and flexible optimization framework that leverages metaheuristic algorithms to automatically optimize CNN configurations for IoT attack detection.Unlike conventional single-objective approaches,the proposed method formulates a global multi-objective fitness function that integrates accuracy,precision,recall,and model size(speed/model complexity penalty)with adjustable weights.This design enables both single-objective and weightedsum multi-objective optimization,allowing adaptive selection of optimal CNN configurations for diverse deployment requirements.Two representativemetaheuristic algorithms,GeneticAlgorithm(GA)and Particle Swarm Optimization(PSO),are employed to optimize CNNhyperparameters and structure.At each generation/iteration,the best configuration is selected as themost balanced solution across optimization objectives,i.e.,the one achieving themaximum value of the global objective function.Experimental validation on two benchmark datasets,Edge-IIoT and CIC-IoT2023,demonstrates that the proposed GA-and PSO-based models significantly enhance detection accuracy(94.8%–98.3%)and generalization compared with manually tuned CNN configurations,while maintaining compact architectures.The results confirm that the multi-objective framework effectively balances predictive performance and computational efficiency.This work establishes a generalizable and adaptive optimization strategy for deep learning-based IoT attack detection and provides a foundation for future hybrid metaheuristic extensions in broader IoT security applications.
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.
