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 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
Nowadays,indistinguishability against adaptive chosen-ciphertext attacks(IND-CCA2)has been widely accepted as a proper security criterion for encryption schemes.In this paper,an efficient conversion is proposed to sat...Nowadays,indistinguishability against adaptive chosen-ciphertext attacks(IND-CCA2)has been widely accepted as a proper security criterion for encryption schemes.In this paper,an efficient conversion is proposed to satisfy the IND-CCA2 security.It uses the random oracle methodology and the idea of hybrid encryption,and can enhance any Diffie-Hellman based encryption scheme,which is only one-way under plaintext-checking attack.Compared with other existing conversions,this conversion has the advantages of short ciphertext and low computation overhead,especially when it is applied to the multi-recipient setting.展开更多
The world airport network（WAN） is one of the networked infrastructures that shape today＇s economic and social activity, so its resilience against incidents affecting the WAN is an important problem. In this paper, ...The world airport network（WAN） is one of the networked infrastructures that shape today＇s economic and social activity, so its resilience against incidents affecting the WAN is an important problem. In this paper, the robustness of air route networks is extended by defining and testing several heuristics to define selection criteria to detect the critical nodes of the WAN.In addition to heuristics based on genetic algorithms and simulated annealing, custom heuristics based on node damage and node betweenness are defined. The most effective heuristic is a multiattack heuristic combining both custom heuristics. Results obtained are of importance not only for advance in the understanding of the structure of complex networks, but also for critical node detection.展开更多
This paper focuses on the instantiation of random oracles in public key encryption schemes. A misunderstanding in the former instantiations is pointed out and analyzed. A method of using this primitive as a substituti...This paper focuses on the instantiation of random oracles in public key encryption schemes. A misunderstanding in the former instantiations is pointed out and analyzed. A method of using this primitive as a substitution of random oracles is also proposed. The partial and full instantiations of random oracles in optimal asymmetric encryption padding （OAEP） implemented by pseudorandom functions are described and the resulted schemes are proven to be indistinguishable secure against adaptive chosen ciphertext attack （IND-CCA2） secure. Using this method, one can transform a practical public key encryption scheme secure in the random oracle model into a standard-model secure scheme. The security of the scheme is based on computational assumptions, which is weaker than decisional assumptions used in Cramer- Shoup like schemes.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 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 National Natural Science Foundation ofChina(60903178)
文摘Nowadays,indistinguishability against adaptive chosen-ciphertext attacks(IND-CCA2)has been widely accepted as a proper security criterion for encryption schemes.In this paper,an efficient conversion is proposed to satisfy the IND-CCA2 security.It uses the random oracle methodology and the idea of hybrid encryption,and can enhance any Diffie-Hellman based encryption scheme,which is only one-way under plaintext-checking attack.Compared with other existing conversions,this conversion has the advantages of short ciphertext and low computation overhead,especially when it is applied to the multi-recipient setting.
文摘The world airport network（WAN） is one of the networked infrastructures that shape today＇s economic and social activity, so its resilience against incidents affecting the WAN is an important problem. In this paper, the robustness of air route networks is extended by defining and testing several heuristics to define selection criteria to detect the critical nodes of the WAN.In addition to heuristics based on genetic algorithms and simulated annealing, custom heuristics based on node damage and node betweenness are defined. The most effective heuristic is a multiattack heuristic combining both custom heuristics. Results obtained are of importance not only for advance in the understanding of the structure of complex networks, but also for critical node detection.
基金Supported by the National Basic Research Program of China (973 Program) (2007CB311201)the National High-Technology Research and Development Program of China (863 Program) (2006AA01Z427)the National Natural Science Foundation of China (60673073)
文摘This paper focuses on the instantiation of random oracles in public key encryption schemes. A misunderstanding in the former instantiations is pointed out and analyzed. A method of using this primitive as a substitution of random oracles is also proposed. The partial and full instantiations of random oracles in optimal asymmetric encryption padding （OAEP） implemented by pseudorandom functions are described and the resulted schemes are proven to be indistinguishable secure against adaptive chosen ciphertext attack （IND-CCA2） secure. Using this method, one can transform a practical public key encryption scheme secure in the random oracle model into a standard-model secure scheme. The security of the scheme is based on computational assumptions, which is weaker than decisional assumptions used in Cramer- Shoup like schemes.
