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
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
False Data Injection Attacks(FDIAs)pose a critical security threat to modern power grids,corrupting state estimation and enabling malicious control actions that can lead to severe consequences,including cascading fail...False Data Injection Attacks(FDIAs)pose a critical security threat to modern power grids,corrupting state estimation and enabling malicious control actions that can lead to severe consequences,including cascading failures,large-scale blackouts,and significant economic losses.While detecting attacks is important,accurately localizing compromised nodes or measurements is even more critical,as it enables timely mitigation,targeted response,and enhanced system resilience beyond what detection alone can offer.Existing research typically models topological features using fixed structures,which can introduce irrelevant information and affect the effectiveness of feature extraction.To address this limitation,this paper proposes an FDIA localization model with adaptive neighborhood selection,which dynamically captures spatial dependencies of the power grid by adjusting node relationships based on data-driven similarities.The improved Transformer is employed to pre-fuse global spatial features of the graph,enriching the feature representation.To improve spatio-temporal correlation extraction for FDIA localization,the proposed model employs dilated causal convolution with a gating mechanism combined with graph convolution to capture and fuse long-range temporal features and adaptive topological features.This fully exploits the temporal dynamics and spatial dependencies inherent in the power grid.Finally,multi-source information is integrated to generate highly robust node embeddings,enhancing FDIA detection and localization.Experiments are conducted on IEEE 14,57,and 118-bus systems,and the results demonstrate that the proposed model substantially improves the accuracy of FDIA localization.Additional experiments are conducted to verify the effectiveness and robustness of the proposed model.展开更多
This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts...This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts perturbation amplitude based on task complexity and optimizes the perturbation direction based on the gradient direction in real time to enhance attack efficiency.Experimental results demonstrate that AMA elevates attack success rates from approximately 78.95%to 89.56%on visual question answering and from78.82%to 84.96%on visual reasoning tasks across representative vision-language benchmarks.These findings demonstrate AMA’s superior attack efficiency and reveal the vulnerability of current visual language models to carefully crafted adversarial examples,underscoring the need to enhance their robustness.展开更多
Studies show that Graph Neural Networks(GNNs)are susceptible to minor perturbations.Therefore,analyzing adversarial attacks on GNNs is crucial in current research.Previous studies used Generative Adversarial Networks ...Studies show that Graph Neural Networks(GNNs)are susceptible to minor perturbations.Therefore,analyzing adversarial attacks on GNNs is crucial in current research.Previous studies used Generative Adversarial Networks to generate a set of fake nodes,injecting them into a clean GNNs to poison the graph structure and evaluate the robustness of GNNs.In the attack process,the computation of new node connections and the attack loss are independent,which affects the attack on the GNN.To improve this,a Fake Node Camouflage Attack based on Mutual Information(FNCAMI)algorithm is proposed.By incorporating Mutual Information(MI)loss,the distribution of nodes injected into the GNNs become more similar to the original nodes,achieving better attack results.Since the loss ratios of GNNs and MI affect performance,we also design an adaptive weighting method.By adjusting the loss weights in real-time through rate changes,larger loss values are obtained,eliminating local optima.The feasibility,effectiveness,and stealthiness of this algorithm are validated on four real datasets.Additionally,we use both global and targeted attacks to test the algorithm’s performance.Comparisons with baseline attack algorithms and ablation experiments demonstrate the efficiency of the FNCAMI algorithm.展开更多
This paper investigates the event-triggered security consensus problem for nonlinear multi-agent systems(MASs)under denial-of-service(Do S)attacks over an undirected graph.A novel adaptive memory observer-based anti-d...This paper investigates the event-triggered security consensus problem for nonlinear multi-agent systems(MASs)under denial-of-service(Do S)attacks over an undirected graph.A novel adaptive memory observer-based anti-disturbance control scheme is presented to improve the observer accuracy by adding a buffer for the system output measurements.Meanwhile,this control scheme can also provide more reasonable control signals when Do S attacks occur.To save network resources,an adaptive memory event-triggered mechanism(AMETM)is also proposed and Zeno behavior is excluded.It is worth mentioning that the AMETM's updates do not require global information.Then,the observer and controller gains are obtained by using the linear matrix inequality(LMI)technique.Finally,simulation examples show the effectiveness of the proposed control scheme.展开更多
In this paper,we present an output regulation method for unknown cyber-physical systems(CPSs)under time-delay attacks in both the sensor-to-controller(S-C)channel and the controller-to-actuator(C-A)channel.The propose...In this paper,we present an output regulation method for unknown cyber-physical systems(CPSs)under time-delay attacks in both the sensor-to-controller(S-C)channel and the controller-to-actuator(C-A)channel.The proposed approach is designed using control inputs and tracking errors which are accessible data.Reinforcement learning is leveraged to update the control gains in real time using policy or value iterations.A thorough stability analysis is conducted and it is found that the proposed controller can sustain the convergence and asymptotic stability even when two channels are attacked.Finally,comparison results with a simulated CPS verify the effectiveness of the proposed output regulation method.展开更多
This paper presents an effective and feasible method for detecting dynamic load-altering attacks(D-LAAs)in a smart grid.First,a smart grid discrete system model is established in view of D-LAAs.Second,an adaptive fadi...This paper presents an effective and feasible method for detecting dynamic load-altering attacks(D-LAAs)in a smart grid.First,a smart grid discrete system model is established in view of D-LAAs.Second,an adaptive fading Kalman filter(AFKF)is designed for estimating the state of the smart grid.The AFKF can completely filter out the Gaussian noise of the power system,and obtain a more accurate state change curve(including consideration of the attack).A Euclidean distance ratio detection algorithm based on the AFKF is proposed for detecting D-LAAs.Amplifying imperceptible D-LAAs through the new Euclidean distance ratio improves the D-LAA detection sensitivity,especially for very weak D-LAA attacks.Finally,the feasibility and effectiveness of the Euclidean distance ratio detection algorithm are verified based on simulations.展开更多
In this paper,a security defense issue is investigated for networked control systems susceptible to stochastic denial of service(DoS) attacks by using the sliding mode control method.To utilize network communication r...In this paper,a security defense issue is investigated for networked control systems susceptible to stochastic denial of service(DoS) attacks by using the sliding mode control method.To utilize network communication resources more effectively,a novel adaptive event-triggered(AET) mechanism is introduced,whose triggering coefficient can be adaptively adjusted according to the evolution trend of system states.Differing from existing event-triggered(ET) mechanisms,the proposed one demonstrates exceptional relevance and flexibility.It is closely related to attack probability,and its triggering coefficient dynamically adjusts depending on the presence or absence of an attack.To leverage attacker information more effectively,a switching-like sliding mode security controller is designed,which can autonomously select different controller gains based on the sliding function representing the attack situation.Sufficient conditions for the existence of the switching-like sliding mode secure controller are presented to ensure the stochastic stability of the system and the reachability of the sliding surface.Compared with existing time-invariant control strategies within the triggered interval,more resilient defense performance can be expected since the correlation with attack information is established in both the proposed AET scheme and the control strategy.Finally,a simulation example is conducted to verify the effectiveness and feasibility of the proposed security control method.展开更多
Aim To present an adaptive missile control system adaped to the external disturbance and the mobility of target movement. Methods Model reference adaptive control (MRAC) was applied and modified in the light of the ...Aim To present an adaptive missile control system adaped to the external disturbance and the mobility of target movement. Methods Model reference adaptive control (MRAC) was applied and modified in the light of the traits of the anti tank missile. Results Simulation results demonstrated this control system satisfied the requirement of anti tank missile of dive overhead attack. Conclusion It is successful to use MRAC in missile control system design, the quality is better than that designed by classical control theory.展开更多
Connected automated vehicles(CAVs)serve as a promising enabler for future intelligent transportation systems because of their capabilities in improving traffic efficiency and driving safety,and reducing fuel consumpti...Connected automated vehicles(CAVs)serve as a promising enabler for future intelligent transportation systems because of their capabilities in improving traffic efficiency and driving safety,and reducing fuel consumption and vehicle emissions.A fundamental issue in CAVs is platooning control that empowers a convoy of CAVs to be cooperatively maneuvered with desired longitudinal spacings and identical velocities on roads.This paper addresses the issue of resilient and safe platooning control of CAVs subject to intermittent denial-of-service(DoS)attacks that disrupt vehicle-to-vehicle communications.First,a heterogeneous and uncertain vehicle longitudinal dynamic model is presented to accommodate a variety of uncertainties,including diverse vehicle masses and engine inertial delays,unknown and nonlinear resistance forces,and a dynamic platoon leader.Then,a resilient and safe distributed longitudinal platooning control law is constructed with an aim to preserve simultaneous individual vehicle stability,attack resilience,platoon safety and scalability.Furthermore,a numerically efficient offline design algorithm for determining the desired platoon control law is developed,under which the platoon resilience against DoS attacks can be maximized but the anticipated stability,safety and scalability requirements remain preserved.Finally,extensive numerical experiments are provided to substantiate the efficacy of the proposed platooning method.展开更多
This paper proposes an adaptively secure solution to certificateless distributed key encapsulation mechanism from pairings by using Canetti＇s adaptive secure key generation scheme based on discrete logarithm. The pro...This paper proposes an adaptively secure solution to certificateless distributed key encapsulation mechanism from pairings by using Canetti＇s adaptive secure key generation scheme based on discrete logarithm. The proposed scheme can withstand adaptive attackers that can choose players for corruption at any time during the run of the protocol, and this kind of attack is powerful and realistic. In contrast, all previously presented threshold certificateless public key cryptosystems are proven secure against the more idealized static adversaries only. They choose and fix the subset of target players before running the protocol. We also prove security of this scheme in the random oracle model.展开更多
In this paper,the fixed-time time-varying formation of heterogeneous multi-agent systems(MASs) based on tracking error observer under denial-of-service(DoS) attacks is investigated.Firstly,the dynamic pinning strategy...In this paper,the fixed-time time-varying formation of heterogeneous multi-agent systems(MASs) based on tracking error observer under denial-of-service(DoS) attacks is investigated.Firstly,the dynamic pinning strategy is used to reconstruct the communication channel for the system that suffers from DoS attacks to prevent the discontinuous transmission information of the communication network from affecting MASs formation.Then,considering that the leader state is not available to each follower under DoS attacks,a fixed-time distributed observer without velocity information is constructed to estimate the tracking error between followers and the leader.Finally,adaptive radial basis function neural network(RBFNN) is used to approximate the unknown ensemble disturbances in the system,and the fixed-time time-varying formation scheme is designed with the constructed observer.The effectiveness of the proposed control algorithm is demonstrated by the numerical simulation.展开更多
Deep learning can train models from a dataset to solve tasks. Although deep learning has attracted much interest owing to the excellent performance, security issues are gradually exposed. Deep learning may be prone to...Deep learning can train models from a dataset to solve tasks. Although deep learning has attracted much interest owing to the excellent performance, security issues are gradually exposed. Deep learning may be prone to the membership inference attack, where the attacker can determine the membership of a given sample. In this paper, we propose a new defense mechanism against membership inference: NoiseDA. In our proposal, a model is not directly trained on a sensitive dataset to alleviate the threat of membership inference attack by leveraging domain adaptation. Besides, a module called Feature Crafter has been designed to reduce the necessary training dataset from 2 to 1, which creates features for domain adaptation training using noise addictive mechanisms. Our experiments have shown that, with the noises properly added by Feature Crafter, our proposal can reduce the success of membership inference with a controllable utility loss.展开更多
Cyber Defense is becoming a major issue for every organization to keep business continuity intact.The presented paper explores the effectiveness of a meta-heuristic optimization algorithm-Artificial Bees Colony Algori...Cyber Defense is becoming a major issue for every organization to keep business continuity intact.The presented paper explores the effectiveness of a meta-heuristic optimization algorithm-Artificial Bees Colony Algorithm(ABC)as an Nature Inspired Cyber Security mechanism to achieve adaptive defense.It experiments on the Denial-Of-Service attack scenarios which involves limiting the traffic flow for each node.Businesses today have adapted their service distribution models to include the use of the Internet,allowing them to effectively manage and interact with their customer data.This shift has created an increased reliance on online services to store vast amounts of confidential customer data,meaning any disruption or outage of these services could be disastrous for the business,leaving them without the knowledge to serve their customers.Adversaries can exploit such an event to gain unauthorized access to the confidential data of the customers.The proposed algorithm utilizes an Adaptive Defense approach to continuously select nodes that could present characteristics of a probable malicious entity.For any changes in network parameters,the cluster of nodes is selected in the prepared solution set as a probable malicious node and the traffic rate with the ratio of packet delivery is managed with respect to the properties of normal nodes to deliver a disaster recovery plan for potential businesses.展开更多
This paper addresses the leader-following consensus problem in multi-agent systems(MASs)with limited communication rates,while also considering sensor and actuator false data injection(FDI)attacks.A distributed event-...This paper addresses the leader-following consensus problem in multi-agent systems(MASs)with limited communication rates,while also considering sensor and actuator false data injection(FDI)attacks.A distributed event-triggered adaptive control protocol is developed to achieve cooperative uniform ultimate boundedness(UUB)in consensus tracking for compromised networked MASs.To implement this protocol,a distributed estimator is first designed to allow followers to estimate the leader's state.Then,adaptive internal controllers are constructed for each follower to mitigate the impact of FDI attack signals.Additionally,an event-triggered transmission logic is introduced to handle the constraints imposed by finite communication rates.Simulation results demonstrate the effectiveness of the proposed approach.展开更多
The rapid progression of the Internet of Things(IoT)technology enables its application across various sectors.However,IoT devices typically acquire inadequate computing power and user interfaces,making them susceptibl...The rapid progression of the Internet of Things(IoT)technology enables its application across various sectors.However,IoT devices typically acquire inadequate computing power and user interfaces,making them susceptible to security threats.One significant risk to cloud networks is Distributed Denial-of-Service(DoS)attacks,where attackers aim to overcome a target system with excessive data and requests.Among these,low-rate DoS(LR-DoS)attacks present a particular challenge to detection.By sending bursts of attacks at irregular intervals,LR-DoS significantly degrades the targeted system’s Quality of Service(QoS).The low-rate nature of these attacks confuses their detection,as they frequently trigger congestion control mechanisms,leading to significant instability in IoT systems.Therefore,to detect the LR-DoS attack,an innovative deep-learning model has been developed for this research work.The standard dataset is utilized to collect the required data.Further,the deep feature extraction process is executed using the Residual Autoencoder with Sparse Attention(ResAE-SA),which helps derive the significant feature required for detection.Ultimately,the Adaptive Dense Recurrent Neural Network(ADRNN)is implemented to detect LR-DoS effectively.To enhance the detection process,the parameters present in the ADRNN are optimized using the Renovated Random Attribute-based Fennec Fox Optimization(RRA-FFA).The proposed optimization reduces the False Discovery Rate and False Positive Rate,maximizing the Matthews Correlation Coefficient from 23,70.8,76.2,84.28 in Dataset 1 and 70.28,73.8,74.1,82.6 in Dataset 2 on EPC-ADRNN,DPO-ADRNN,GTO-ADRNN,FFA-ADRNN respectively to 95.8 on Dataset 1 and 91.7 on Dataset 2 in proposed model.At batch size 4,the accuracy of the designed RRA-FFA-ADRNN model progressed by 9.2%to GTO-ADRNN,11.6%to EFC-ADRNN,10.9%to DPO-ADRNN,and 4%to FFA-ADRNN for Dataset 1.The accuracy of the proposed RRA-FFA-ADRNN is boosted by 12.9%,9.09%,11.6%,and 10.9%over FFCNN,SVM,RNN,and DRNN,using Dataset 2,showing a better improvement in accuracy with that of the proposed RRA-FFA-ADRNN model with 95.7%using Dataset 1 and 94.1%with Dataset 2,which is better than the existing baseline models.展开更多
This paper studies the challenging problem of model-free adaptive(MFA)security tracking control for nonlinear multi-agent systems(MASs)under mixed denial-of-service(DoS)attacks.First,in contrast to existing results fo...This paper studies the challenging problem of model-free adaptive(MFA)security tracking control for nonlinear multi-agent systems(MASs)under mixed denial-of-service(DoS)attacks.First,in contrast to existing results focusing on DoS attacks with one monotonic characteristic only,a more realistic mixed DoS attacks model is constructed,which can describe multiple types of DoS attacks and reflect the real attack strategy.Second,to mitigate the negative effect of mixed DoS attacks on control performance,an effective memory event-triggered mechanism is considered.Compared with existing event-triggered schemes,the developed memory event-triggered scheme utilizes historically triggered data and allows the released data to adjust adaptively using the long-term changes of the system state,which optimizes the utilization of communication resources and withstands the effect of mixed DoS attacks.Further,with the help of a dynamic linearization technique based on memory eventtriggered strategy,a linearized data model of the MASs is first established only depending on input/output information.Then,an improved memory event-triggered MFA security tracking control scheme is developed so that MASs can guarantee the tracking errors of all agents are bounded under mixed DoS attacks.Finally,a simulation example is presented of the designed MFA security tracking control method to illustrate its usefulness and advantages.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.
基金supported by National Key Research and Development Plan of China(No.2022YFB3103304).
文摘False Data Injection Attacks(FDIAs)pose a critical security threat to modern power grids,corrupting state estimation and enabling malicious control actions that can lead to severe consequences,including cascading failures,large-scale blackouts,and significant economic losses.While detecting attacks is important,accurately localizing compromised nodes or measurements is even more critical,as it enables timely mitigation,targeted response,and enhanced system resilience beyond what detection alone can offer.Existing research typically models topological features using fixed structures,which can introduce irrelevant information and affect the effectiveness of feature extraction.To address this limitation,this paper proposes an FDIA localization model with adaptive neighborhood selection,which dynamically captures spatial dependencies of the power grid by adjusting node relationships based on data-driven similarities.The improved Transformer is employed to pre-fuse global spatial features of the graph,enriching the feature representation.To improve spatio-temporal correlation extraction for FDIA localization,the proposed model employs dilated causal convolution with a gating mechanism combined with graph convolution to capture and fuse long-range temporal features and adaptive topological features.This fully exploits the temporal dynamics and spatial dependencies inherent in the power grid.Finally,multi-source information is integrated to generate highly robust node embeddings,enhancing FDIA detection and localization.Experiments are conducted on IEEE 14,57,and 118-bus systems,and the results demonstrate that the proposed model substantially improves the accuracy of FDIA localization.Additional experiments are conducted to verify the effectiveness and robustness of the proposed model.
基金funded by the Natural Science Foundation of Jiangsu Province(Program BK20240699)National Natural Science Foundation of China(Program 62402228).
文摘This article proposes an innovative adversarial attack method,AMA(Adaptive Multimodal Attack),which introduces an adaptive feedback mechanism by dynamically adjusting the perturbation strength.Specifically,AMA adjusts perturbation amplitude based on task complexity and optimizes the perturbation direction based on the gradient direction in real time to enhance attack efficiency.Experimental results demonstrate that AMA elevates attack success rates from approximately 78.95%to 89.56%on visual question answering and from78.82%to 84.96%on visual reasoning tasks across representative vision-language benchmarks.These findings demonstrate AMA’s superior attack efficiency and reveal the vulnerability of current visual language models to carefully crafted adversarial examples,underscoring the need to enhance their robustness.
基金supported by the Natural Science Basic Research Plan in Shaanxi Province of China(Program No.2022JM-381,2017JQ6070)National Natural Science Foundation of China(Grant No.61703256),Foundation of State Key Laboratory of Public Big Data(No.PBD2022-08)the Fundamental Research Funds for the Central Universities,China(Program No.GK202201014,GK202202003,GK201803020).
文摘Studies show that Graph Neural Networks(GNNs)are susceptible to minor perturbations.Therefore,analyzing adversarial attacks on GNNs is crucial in current research.Previous studies used Generative Adversarial Networks to generate a set of fake nodes,injecting them into a clean GNNs to poison the graph structure and evaluate the robustness of GNNs.In the attack process,the computation of new node connections and the attack loss are independent,which affects the attack on the GNN.To improve this,a Fake Node Camouflage Attack based on Mutual Information(FNCAMI)algorithm is proposed.By incorporating Mutual Information(MI)loss,the distribution of nodes injected into the GNNs become more similar to the original nodes,achieving better attack results.Since the loss ratios of GNNs and MI affect performance,we also design an adaptive weighting method.By adjusting the loss weights in real-time through rate changes,larger loss values are obtained,eliminating local optima.The feasibility,effectiveness,and stealthiness of this algorithm are validated on four real datasets.Additionally,we use both global and targeted attacks to test the algorithm’s performance.Comparisons with baseline attack algorithms and ablation experiments demonstrate the efficiency of the FNCAMI algorithm.
基金supported by the National Natural Science Foundation of China(61773056)the Scientific and Technological Innovation Foundation of Shunde Graduate School,University of Science and Technology Beijing(USTB)(BK19AE018)+2 种基金the Fundamental Research Funds for the Central Universities of USTB(FRF-TP-20-09B,230201606500061,FRF-DF-20-35,FRF-BD-19-002A)supported by Zhejiang Natural Science Foundation(LD21F030001)supported by the National Research Foundation of Korea(NRF)grant funded by the Korea government(Ministry of Science and Information and Communications Technology)(NRF-2020R1A2C1005449)。
文摘This paper investigates the event-triggered security consensus problem for nonlinear multi-agent systems(MASs)under denial-of-service(Do S)attacks over an undirected graph.A novel adaptive memory observer-based anti-disturbance control scheme is presented to improve the observer accuracy by adding a buffer for the system output measurements.Meanwhile,this control scheme can also provide more reasonable control signals when Do S attacks occur.To save network resources,an adaptive memory event-triggered mechanism(AMETM)is also proposed and Zeno behavior is excluded.It is worth mentioning that the AMETM's updates do not require global information.Then,the observer and controller gains are obtained by using the linear matrix inequality(LMI)technique.Finally,simulation examples show the effectiveness of the proposed control scheme.
基金the National Natural Science Foundation of China(Nos.61973277,62073292)the Zhejiang Provincial Natural Science Foundation of China(No.LR20F030004).
文摘In this paper,we present an output regulation method for unknown cyber-physical systems(CPSs)under time-delay attacks in both the sensor-to-controller(S-C)channel and the controller-to-actuator(C-A)channel.The proposed approach is designed using control inputs and tracking errors which are accessible data.Reinforcement learning is leveraged to update the control gains in real time using policy or value iterations.A thorough stability analysis is conducted and it is found that the proposed controller can sustain the convergence and asymptotic stability even when two channels are attacked.Finally,comparison results with a simulated CPS verify the effectiveness of the proposed output regulation method.
基金the Science and Technology Project of the State Grid Shandong Electric Power Company:Research on the vulnerability and prevention of the electrical cyber-physical monitoring system based on interdependent networksthe National Natural Science Foundation of China(61873057)and the Education Department of Jilin Province(JJKH20200118KJ).
文摘This paper presents an effective and feasible method for detecting dynamic load-altering attacks(D-LAAs)in a smart grid.First,a smart grid discrete system model is established in view of D-LAAs.Second,an adaptive fading Kalman filter(AFKF)is designed for estimating the state of the smart grid.The AFKF can completely filter out the Gaussian noise of the power system,and obtain a more accurate state change curve(including consideration of the attack).A Euclidean distance ratio detection algorithm based on the AFKF is proposed for detecting D-LAAs.Amplifying imperceptible D-LAAs through the new Euclidean distance ratio improves the D-LAA detection sensitivity,especially for very weak D-LAA attacks.Finally,the feasibility and effectiveness of the Euclidean distance ratio detection algorithm are verified based on simulations.
基金supported in part by Shanghai Natural Science Foundation(24ZR1454700)the National Natural Science Foundation of China(62503331,62533016,62573279,62173231,62203288)Shanghai Pujiang Program(23PJD033)。
文摘In this paper,a security defense issue is investigated for networked control systems susceptible to stochastic denial of service(DoS) attacks by using the sliding mode control method.To utilize network communication resources more effectively,a novel adaptive event-triggered(AET) mechanism is introduced,whose triggering coefficient can be adaptively adjusted according to the evolution trend of system states.Differing from existing event-triggered(ET) mechanisms,the proposed one demonstrates exceptional relevance and flexibility.It is closely related to attack probability,and its triggering coefficient dynamically adjusts depending on the presence or absence of an attack.To leverage attacker information more effectively,a switching-like sliding mode security controller is designed,which can autonomously select different controller gains based on the sliding function representing the attack situation.Sufficient conditions for the existence of the switching-like sliding mode secure controller are presented to ensure the stochastic stability of the system and the reachability of the sliding surface.Compared with existing time-invariant control strategies within the triggered interval,more resilient defense performance can be expected since the correlation with attack information is established in both the proposed AET scheme and the control strategy.Finally,a simulation example is conducted to verify the effectiveness and feasibility of the proposed security control method.
文摘Aim To present an adaptive missile control system adaped to the external disturbance and the mobility of target movement. Methods Model reference adaptive control (MRAC) was applied and modified in the light of the traits of the anti tank missile. Results Simulation results demonstrated this control system satisfied the requirement of anti tank missile of dive overhead attack. Conclusion It is successful to use MRAC in missile control system design, the quality is better than that designed by classical control theory.
基金supported in part by Australian Research Council Discovery Early Career Researcher Award(DE210100273)。
文摘Connected automated vehicles(CAVs)serve as a promising enabler for future intelligent transportation systems because of their capabilities in improving traffic efficiency and driving safety,and reducing fuel consumption and vehicle emissions.A fundamental issue in CAVs is platooning control that empowers a convoy of CAVs to be cooperatively maneuvered with desired longitudinal spacings and identical velocities on roads.This paper addresses the issue of resilient and safe platooning control of CAVs subject to intermittent denial-of-service(DoS)attacks that disrupt vehicle-to-vehicle communications.First,a heterogeneous and uncertain vehicle longitudinal dynamic model is presented to accommodate a variety of uncertainties,including diverse vehicle masses and engine inertial delays,unknown and nonlinear resistance forces,and a dynamic platoon leader.Then,a resilient and safe distributed longitudinal platooning control law is constructed with an aim to preserve simultaneous individual vehicle stability,attack resilience,platoon safety and scalability.Furthermore,a numerically efficient offline design algorithm for determining the desired platoon control law is developed,under which the platoon resilience against DoS attacks can be maximized but the anticipated stability,safety and scalability requirements remain preserved.Finally,extensive numerical experiments are provided to substantiate the efficacy of the proposed platooning method.
基金the National Basic Research Program(973)of China(No.2007CB311201)the National High Technology Research and Development Program(863) of China(Nos.2006AA01Z422,2007AA01Z456)
文摘This paper proposes an adaptively secure solution to certificateless distributed key encapsulation mechanism from pairings by using Canetti＇s adaptive secure key generation scheme based on discrete logarithm. The proposed scheme can withstand adaptive attackers that can choose players for corruption at any time during the run of the protocol, and this kind of attack is powerful and realistic. In contrast, all previously presented threshold certificateless public key cryptosystems are proven secure against the more idealized static adversaries only. They choose and fix the subset of target players before running the protocol. We also prove security of this scheme in the random oracle model.
文摘In this paper,the fixed-time time-varying formation of heterogeneous multi-agent systems(MASs) based on tracking error observer under denial-of-service(DoS) attacks is investigated.Firstly,the dynamic pinning strategy is used to reconstruct the communication channel for the system that suffers from DoS attacks to prevent the discontinuous transmission information of the communication network from affecting MASs formation.Then,considering that the leader state is not available to each follower under DoS attacks,a fixed-time distributed observer without velocity information is constructed to estimate the tracking error between followers and the leader.Finally,adaptive radial basis function neural network(RBFNN) is used to approximate the unknown ensemble disturbances in the system,and the fixed-time time-varying formation scheme is designed with the constructed observer.The effectiveness of the proposed control algorithm is demonstrated by the numerical simulation.
文摘Deep learning can train models from a dataset to solve tasks. Although deep learning has attracted much interest owing to the excellent performance, security issues are gradually exposed. Deep learning may be prone to the membership inference attack, where the attacker can determine the membership of a given sample. In this paper, we propose a new defense mechanism against membership inference: NoiseDA. In our proposal, a model is not directly trained on a sensitive dataset to alleviate the threat of membership inference attack by leveraging domain adaptation. Besides, a module called Feature Crafter has been designed to reduce the necessary training dataset from 2 to 1, which creates features for domain adaptation training using noise addictive mechanisms. Our experiments have shown that, with the noises properly added by Feature Crafter, our proposal can reduce the success of membership inference with a controllable utility loss.
文摘Cyber Defense is becoming a major issue for every organization to keep business continuity intact.The presented paper explores the effectiveness of a meta-heuristic optimization algorithm-Artificial Bees Colony Algorithm(ABC)as an Nature Inspired Cyber Security mechanism to achieve adaptive defense.It experiments on the Denial-Of-Service attack scenarios which involves limiting the traffic flow for each node.Businesses today have adapted their service distribution models to include the use of the Internet,allowing them to effectively manage and interact with their customer data.This shift has created an increased reliance on online services to store vast amounts of confidential customer data,meaning any disruption or outage of these services could be disastrous for the business,leaving them without the knowledge to serve their customers.Adversaries can exploit such an event to gain unauthorized access to the confidential data of the customers.The proposed algorithm utilizes an Adaptive Defense approach to continuously select nodes that could present characteristics of a probable malicious entity.For any changes in network parameters,the cluster of nodes is selected in the prepared solution set as a probable malicious node and the traffic rate with the ratio of packet delivery is managed with respect to the properties of normal nodes to deliver a disaster recovery plan for potential businesses.
文摘This paper addresses the leader-following consensus problem in multi-agent systems(MASs)with limited communication rates,while also considering sensor and actuator false data injection(FDI)attacks.A distributed event-triggered adaptive control protocol is developed to achieve cooperative uniform ultimate boundedness(UUB)in consensus tracking for compromised networked MASs.To implement this protocol,a distributed estimator is first designed to allow followers to estimate the leader's state.Then,adaptive internal controllers are constructed for each follower to mitigate the impact of FDI attack signals.Additionally,an event-triggered transmission logic is introduced to handle the constraints imposed by finite communication rates.Simulation results demonstrate the effectiveness of the proposed approach.
基金funded by the Ministry of Higher Education Malaysia,Fundamental Research Grant Scheme(FRGS),FRGS/1/2024/ICT07/UPNM/02/1.
文摘The rapid progression of the Internet of Things(IoT)technology enables its application across various sectors.However,IoT devices typically acquire inadequate computing power and user interfaces,making them susceptible to security threats.One significant risk to cloud networks is Distributed Denial-of-Service(DoS)attacks,where attackers aim to overcome a target system with excessive data and requests.Among these,low-rate DoS(LR-DoS)attacks present a particular challenge to detection.By sending bursts of attacks at irregular intervals,LR-DoS significantly degrades the targeted system’s Quality of Service(QoS).The low-rate nature of these attacks confuses their detection,as they frequently trigger congestion control mechanisms,leading to significant instability in IoT systems.Therefore,to detect the LR-DoS attack,an innovative deep-learning model has been developed for this research work.The standard dataset is utilized to collect the required data.Further,the deep feature extraction process is executed using the Residual Autoencoder with Sparse Attention(ResAE-SA),which helps derive the significant feature required for detection.Ultimately,the Adaptive Dense Recurrent Neural Network(ADRNN)is implemented to detect LR-DoS effectively.To enhance the detection process,the parameters present in the ADRNN are optimized using the Renovated Random Attribute-based Fennec Fox Optimization(RRA-FFA).The proposed optimization reduces the False Discovery Rate and False Positive Rate,maximizing the Matthews Correlation Coefficient from 23,70.8,76.2,84.28 in Dataset 1 and 70.28,73.8,74.1,82.6 in Dataset 2 on EPC-ADRNN,DPO-ADRNN,GTO-ADRNN,FFA-ADRNN respectively to 95.8 on Dataset 1 and 91.7 on Dataset 2 in proposed model.At batch size 4,the accuracy of the designed RRA-FFA-ADRNN model progressed by 9.2%to GTO-ADRNN,11.6%to EFC-ADRNN,10.9%to DPO-ADRNN,and 4%to FFA-ADRNN for Dataset 1.The accuracy of the proposed RRA-FFA-ADRNN is boosted by 12.9%,9.09%,11.6%,and 10.9%over FFCNN,SVM,RNN,and DRNN,using Dataset 2,showing a better improvement in accuracy with that of the proposed RRA-FFA-ADRNN model with 95.7%using Dataset 1 and 94.1%with Dataset 2,which is better than the existing baseline models.
基金supported by the National Natural Science Foundation of China(Grant Nos.62303125,62373113,62433018,62433014,62303121,62373111)the Guangdong Basic and Applied Basic Research Foundation(Grant Nos.2022A1515110949,2023A1515011527,2023B1515120010,2025A1515011343,2023A1515010855)the Science and Technology Planning Project of Guangzhou City(Grant No.2025A04J4336)。
文摘This paper studies the challenging problem of model-free adaptive(MFA)security tracking control for nonlinear multi-agent systems(MASs)under mixed denial-of-service(DoS)attacks.First,in contrast to existing results focusing on DoS attacks with one monotonic characteristic only,a more realistic mixed DoS attacks model is constructed,which can describe multiple types of DoS attacks and reflect the real attack strategy.Second,to mitigate the negative effect of mixed DoS attacks on control performance,an effective memory event-triggered mechanism is considered.Compared with existing event-triggered schemes,the developed memory event-triggered scheme utilizes historically triggered data and allows the released data to adjust adaptively using the long-term changes of the system state,which optimizes the utilization of communication resources and withstands the effect of mixed DoS attacks.Further,with the help of a dynamic linearization technique based on memory eventtriggered strategy,a linearized data model of the MASs is first established only depending on input/output information.Then,an improved memory event-triggered MFA security tracking control scheme is developed so that MASs can guarantee the tracking errors of all agents are bounded under mixed DoS attacks.Finally,a simulation example is presented of the designed MFA security tracking control method to illustrate its usefulness and advantages.
