Adversarial distillation(AD)has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training.However,fixed sample-agnostic and student-egocentric atta...Adversarial distillation(AD)has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training.However,fixed sample-agnostic and student-egocentric attack strategies are unsuitable for distillation.Additionally,the reliability of guidance from static teachers diminishes as target models become more robust.This paper proposes an AD method called Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation(LDAS&ET-AD).Firstly,a learnable distillation attack strategies generating mechanism is developed to automatically generate sample-dependent attack strategies tailored for distillation.A strategy model is introduced to produce attack strategies that enable adversarial examples(AEs)to be created in areas where the target model significantly diverges from the teachers by competing with the target model in minimizing or maximizing the AD loss.Secondly,a teacher evolution strategy is introduced to enhance the reliability and effectiveness of knowledge in improving the generalization performance of the target model.By calculating the experimentally updated target model’s validation performance on both clean samples and AEs,the impact of distillation from each training sample and AE on the target model’s generalization and robustness abilities is assessed to serve as feedback to fine-tune standard and robust teachers accordingly.Experiments evaluate the performance of LDAS&ET-AD against different adversarial attacks on the CIFAR-10 and CIFAR-100 datasets.The experimental results demonstrate that the proposed method achieves a robust precision of 45.39%and 42.63%against AutoAttack(AA)on the CIFAR-10 dataset for ResNet-18 and MobileNet-V2,respectively,marking an improvement of 2.31%and 3.49%over the baseline method.In comparison to state-of-the-art adversarial defense techniques,our method surpasses Introspective Adversarial Distillation,the top-performing method in terms of robustness under AA attack for the CIFAR-10 dataset,with enhancements of 1.40%and 1.43%for ResNet-18 and MobileNet-V2,respectively.These findings demonstrate the effectiveness of our proposed method in enhancing the robustness of deep learning networks(DNNs)against prevalent adversarial attacks when compared to other competing methods.In conclusion,LDAS&ET-AD provides reliable and informative soft labels to one of the most promising defense methods,AT,alleviating the limitations of untrusted teachers and unsuitable AEs in existing AD techniques.We hope this paper promotes the development of DNNs in real-world trust-sensitive fields and helps ensure a more secure and dependable future for artificial intelligence systems.展开更多
A definition of self-determined priority is used in airfight decision firstly. A scheme of grouping the whole fighters is introduced, and the principle of target assignment and fire control is designed. Based on the ...A definition of self-determined priority is used in airfight decision firstly. A scheme of grouping the whole fighters is introduced, and the principle of target assignment and fire control is designed. Based on the neutral network, the decision algorithm is derived and the whole coordinated decision system is simulated. Secondly an algorithm for missile-attacking area is described and its calculational result is obtained under initial conditions. Then the attacking of missile is realized by the proportion guidance. Finally, a multi-target attack system. The system includes airfight decision, estimation of missile attack area and calculation of missile attack procedure. A digital simulation demonstrates that the airfight decision algorithm is correct. The methods have important reference values for the study of fire control system of the fourth generation fighter.展开更多
This paper considers the problem of generating a flight trajectory for a single fixed-wing unmanned combat aerial vehicle （UCAV） performing an air-to-surface multi-target attack （A/SMTA） mission using satellite-gu...This paper considers the problem of generating a flight trajectory for a single fixed-wing unmanned combat aerial vehicle （UCAV） performing an air-to-surface multi-target attack （A/SMTA） mission using satellite-guided bombs. First, this problem is formulated as a variant of the traveling salesman problem （TSP）, called the dynamic-constrained TSP with neighborhoods （DCT- SPN）. Then, a hierarchical hybrid approach, which partitions the planning algorithm into a roadmap planning layer and an optimal control layer, is proposed to solve the DCTSPN. In the roadmap planning layer, a novel algorithm based on an updatable proba- bilistic roadmap （PRM） is presented, which operates by randomly sampling a finite set of vehicle states from continuous state space in order to reduce the complicated trajectory planning problem to planning on a finite directed graph. In the optimal control layer, a collision-free state-to-state trajectory planner based on the Gauss pseudospectral method is developed, which can generate both dynamically feasible and optimal flight trajectories. The entire process of solving a DCTSPN consists of two phases. First, in the offline preprocessing phase, the algorithm constructs a PRM, and then converts the original problem into a standard asymmet- ric TSP （ATSP）. Second, in the online querying phase, the costs of directed edges in PRM are updated first, and a fast heuristic searching algorithm is then used to solve the ATSP. Numerical experiments indicate that the algorithm proposed in this paper can generate both feasible and near-optimal solutions quickly for online purposes.展开更多
A kind of attack strategy based on a probabilistic cloning machine is proposed in this letter. The security of BB84 and the six-state quantum key distribution protocols under this attack is studied by theoretic analys...A kind of attack strategy based on a probabilistic cloning machine is proposed in this letter. The security of BB84 and the six-state quantum key distribution protocols under this attack is studied by theoretic analyses and corroborated by simulations. It is concluded that the quantum key distribution protocols still have an asymptotic perfect security even if the eavesdropper adopts the proposed attack strategy.展开更多
Cloud computing involves remote server deployments with public net-work infrastructures that allow clients to access computational resources.Virtual Machines(VMs)are supplied on requests and launched without interacti...Cloud computing involves remote server deployments with public net-work infrastructures that allow clients to access computational resources.Virtual Machines(VMs)are supplied on requests and launched without interactions from service providers.Intruders can target these servers and establish malicious con-nections on VMs for carrying out attacks on other clustered VMs.The existing system has issues with execution time and false-positive rates.Hence,the overall system performance is degraded considerably.The proposed approach is designed to eliminate Cross-VM side attacks and VM escape and hide the server’s position so that the opponent cannot track the target server beyond a certain point.Every request is passed from source to destination via one broadcast domain to confuse the opponent and avoid them from tracking the server’s position.Allocation of SECURITY Resources accepts a safety game in a simple format as input andfinds the best coverage vector for the opponent using a Stackelberg Equilibrium(SSE)technique.A Mixed Integer Linear Programming(MILP)framework is used in the algorithm.The VM challenge is reduced by afirewall-based controlling mechanism combining behavior-based detection and signature-based virus detection.The pro-posed method is focused on detecting malware attacks effectively and providing better security for the VMs.Finally,the experimental results indicate that the pro-posed security method is efficient.It consumes minimum execution time,better false positive rate,accuracy,and memory usage than the conventional approach.展开更多
纵向联邦学习(Vertical federated learning,VFL)是一种新兴的分布式机器学习技术,在保障隐私性的前提下,利用分散在各个机构的数据实现机器学习模型的联合训练.纵向联邦学习被广泛应用于工业互联网、金融借贷和医疗诊断等诸多领域中,...纵向联邦学习(Vertical federated learning,VFL)是一种新兴的分布式机器学习技术,在保障隐私性的前提下,利用分散在各个机构的数据实现机器学习模型的联合训练.纵向联邦学习被广泛应用于工业互联网、金融借贷和医疗诊断等诸多领域中,因此保证其隐私安全性具有重要意义.首先,针对纵向联邦学习协议中由于参与方交换的嵌入表示造成的隐私泄漏风险,研究由协作者发起的通用的属性推断攻击.攻击者利用辅助数据和嵌入表示训练一个攻击模型,然后利用训练完成的攻击模型窃取参与方的隐私属性.实验结果表明,纵向联邦学习在训练推理阶段产生的嵌入表示容易泄漏数据隐私.为了应对上述隐私泄漏风险,提出一种基于最大−最小策略的纵向联邦学习隐私保护方法(Privacy preservation method for vertical federated learning based on max-min strategy,PPVFL),其引入梯度正则组件保证训练过程主任务的预测性能,同时引入重构组件掩藏参与方嵌入表示中包含的隐私属性信息.最后,在钢板缺陷诊断工业场景的实验结果表明,相比于没有任何防御方法的VFL,隐私保护方法将攻击推断准确度从95%下降到55%以下,接近于随机猜测的水平,同时主任务预测准确率仅下降2%.展开更多
基金the National Key Research and Development Program of China(2021YFB1006200)Major Science and Technology Project of Henan Province in China(221100211200).Grant was received by S.Li.
文摘Adversarial distillation(AD)has emerged as a potential solution to tackle the challenging optimization problem of loss with hard labels in adversarial training.However,fixed sample-agnostic and student-egocentric attack strategies are unsuitable for distillation.Additionally,the reliability of guidance from static teachers diminishes as target models become more robust.This paper proposes an AD method called Learnable Distillation Attack Strategies and Evolvable Teachers Adversarial Distillation(LDAS&ET-AD).Firstly,a learnable distillation attack strategies generating mechanism is developed to automatically generate sample-dependent attack strategies tailored for distillation.A strategy model is introduced to produce attack strategies that enable adversarial examples(AEs)to be created in areas where the target model significantly diverges from the teachers by competing with the target model in minimizing or maximizing the AD loss.Secondly,a teacher evolution strategy is introduced to enhance the reliability and effectiveness of knowledge in improving the generalization performance of the target model.By calculating the experimentally updated target model’s validation performance on both clean samples and AEs,the impact of distillation from each training sample and AE on the target model’s generalization and robustness abilities is assessed to serve as feedback to fine-tune standard and robust teachers accordingly.Experiments evaluate the performance of LDAS&ET-AD against different adversarial attacks on the CIFAR-10 and CIFAR-100 datasets.The experimental results demonstrate that the proposed method achieves a robust precision of 45.39%and 42.63%against AutoAttack(AA)on the CIFAR-10 dataset for ResNet-18 and MobileNet-V2,respectively,marking an improvement of 2.31%and 3.49%over the baseline method.In comparison to state-of-the-art adversarial defense techniques,our method surpasses Introspective Adversarial Distillation,the top-performing method in terms of robustness under AA attack for the CIFAR-10 dataset,with enhancements of 1.40%and 1.43%for ResNet-18 and MobileNet-V2,respectively.These findings demonstrate the effectiveness of our proposed method in enhancing the robustness of deep learning networks(DNNs)against prevalent adversarial attacks when compared to other competing methods.In conclusion,LDAS&ET-AD provides reliable and informative soft labels to one of the most promising defense methods,AT,alleviating the limitations of untrusted teachers and unsuitable AEs in existing AD techniques.We hope this paper promotes the development of DNNs in real-world trust-sensitive fields and helps ensure a more secure and dependable future for artificial intelligence systems.
文摘A definition of self-determined priority is used in airfight decision firstly. A scheme of grouping the whole fighters is introduced, and the principle of target assignment and fire control is designed. Based on the neutral network, the decision algorithm is derived and the whole coordinated decision system is simulated. Secondly an algorithm for missile-attacking area is described and its calculational result is obtained under initial conditions. Then the attacking of missile is realized by the proportion guidance. Finally, a multi-target attack system. The system includes airfight decision, estimation of missile attack area and calculation of missile attack procedure. A digital simulation demonstrates that the airfight decision algorithm is correct. The methods have important reference values for the study of fire control system of the fourth generation fighter.
文摘This paper considers the problem of generating a flight trajectory for a single fixed-wing unmanned combat aerial vehicle （UCAV） performing an air-to-surface multi-target attack （A/SMTA） mission using satellite-guided bombs. First, this problem is formulated as a variant of the traveling salesman problem （TSP）, called the dynamic-constrained TSP with neighborhoods （DCT- SPN）. Then, a hierarchical hybrid approach, which partitions the planning algorithm into a roadmap planning layer and an optimal control layer, is proposed to solve the DCTSPN. In the roadmap planning layer, a novel algorithm based on an updatable proba- bilistic roadmap （PRM） is presented, which operates by randomly sampling a finite set of vehicle states from continuous state space in order to reduce the complicated trajectory planning problem to planning on a finite directed graph. In the optimal control layer, a collision-free state-to-state trajectory planner based on the Gauss pseudospectral method is developed, which can generate both dynamically feasible and optimal flight trajectories. The entire process of solving a DCTSPN consists of two phases. First, in the offline preprocessing phase, the algorithm constructs a PRM, and then converts the original problem into a standard asymmet- ric TSP （ATSP）. Second, in the online querying phase, the costs of directed edges in PRM are updated first, and a fast heuristic searching algorithm is then used to solve the ATSP. Numerical experiments indicate that the algorithm proposed in this paper can generate both feasible and near-optimal solutions quickly for online purposes.
文摘A kind of attack strategy based on a probabilistic cloning machine is proposed in this letter. The security of BB84 and the six-state quantum key distribution protocols under this attack is studied by theoretic analyses and corroborated by simulations. It is concluded that the quantum key distribution protocols still have an asymptotic perfect security even if the eavesdropper adopts the proposed attack strategy.
文摘Cloud computing involves remote server deployments with public net-work infrastructures that allow clients to access computational resources.Virtual Machines(VMs)are supplied on requests and launched without interactions from service providers.Intruders can target these servers and establish malicious con-nections on VMs for carrying out attacks on other clustered VMs.The existing system has issues with execution time and false-positive rates.Hence,the overall system performance is degraded considerably.The proposed approach is designed to eliminate Cross-VM side attacks and VM escape and hide the server’s position so that the opponent cannot track the target server beyond a certain point.Every request is passed from source to destination via one broadcast domain to confuse the opponent and avoid them from tracking the server’s position.Allocation of SECURITY Resources accepts a safety game in a simple format as input andfinds the best coverage vector for the opponent using a Stackelberg Equilibrium(SSE)technique.A Mixed Integer Linear Programming(MILP)framework is used in the algorithm.The VM challenge is reduced by afirewall-based controlling mechanism combining behavior-based detection and signature-based virus detection.The pro-posed method is focused on detecting malware attacks effectively and providing better security for the VMs.Finally,the experimental results indicate that the pro-posed security method is efficient.It consumes minimum execution time,better false positive rate,accuracy,and memory usage than the conventional approach.
文摘纵向联邦学习(Vertical federated learning,VFL)是一种新兴的分布式机器学习技术,在保障隐私性的前提下,利用分散在各个机构的数据实现机器学习模型的联合训练.纵向联邦学习被广泛应用于工业互联网、金融借贷和医疗诊断等诸多领域中,因此保证其隐私安全性具有重要意义.首先,针对纵向联邦学习协议中由于参与方交换的嵌入表示造成的隐私泄漏风险,研究由协作者发起的通用的属性推断攻击.攻击者利用辅助数据和嵌入表示训练一个攻击模型,然后利用训练完成的攻击模型窃取参与方的隐私属性.实验结果表明,纵向联邦学习在训练推理阶段产生的嵌入表示容易泄漏数据隐私.为了应对上述隐私泄漏风险,提出一种基于最大−最小策略的纵向联邦学习隐私保护方法(Privacy preservation method for vertical federated learning based on max-min strategy,PPVFL),其引入梯度正则组件保证训练过程主任务的预测性能,同时引入重构组件掩藏参与方嵌入表示中包含的隐私属性信息.最后,在钢板缺陷诊断工业场景的实验结果表明,相比于没有任何防御方法的VFL,隐私保护方法将攻击推断准确度从95%下降到55%以下,接近于随机猜测的水平,同时主任务预测准确率仅下降2%.
