Medical image segmentation is a powerful and evolving technology in medical diagnosis.In fact,it has been identified as a very effective tool to support and accompany doctors in their fight against the spread of the c...Medical image segmentation is a powerful and evolving technology in medical diagnosis.In fact,it has been identified as a very effective tool to support and accompany doctors in their fight against the spread of the coronavirus(COVID-19).Various techniques have been utilized for COVID-19 image segmentation,including Multilevel Thresholding(MLT)-based meta-heuristics,which are considered crucial in addressing this issue.However,despite their importance,meta-heuristics have significant limitations.Specifically,the imbalance between exploration and exploitation,as well as premature convergence,can cause the optimization process to become stuck in local optima,resulting in unsatisfactory segmentation results.In this paper,an enhanced War Strategy Chimp Optimization Algorithm(WSChOA)is proposed to address MLT problems.Two strategies are incorporated into the traditional Chimp Optimization Algorithm.Golden update mechanism that provides diversity in the population.Additionally,the attack and defense strategies are incorporated to improve the search space leading to avoiding local optima.The experimental results were conducted by comparing WSChoA with recent and well-known algorithms using various evaluation metrics such as Feature Similarity Index(FSIM),Structural Similarity Index(SSIM),Peak signal-to-Noise Ratio(PSNR),Standard deviation(STD),Freidman Test(FT),and Wilcoxon Sign Rank Test(WSRT).The results obtained by WSChoA surpassed those of other optimization techniques in terms of robustness and accuracy,indicating that it is a powerful tool for image segmentation.展开更多
Deep Neural Networks(DNNs)are integral to various aspects of modern life,enhancing work efficiency.Nonethe-less,their susceptibility to diverse attack methods,including backdoor attacks,raises security concerns.We aim...Deep Neural Networks(DNNs)are integral to various aspects of modern life,enhancing work efficiency.Nonethe-less,their susceptibility to diverse attack methods,including backdoor attacks,raises security concerns.We aim to investigate backdoor attack methods for image categorization tasks,to promote the development of DNN towards higher security.Research on backdoor attacks currently faces significant challenges due to the distinct and abnormal data patterns of malicious samples,and the meticulous data screening by developers,hindering practical attack implementation.To overcome these challenges,this study proposes a Gaussian Noise-Targeted Universal Adversarial Perturbation(GN-TUAP)algorithm.This approach restricts the direction of perturbations and normalizes abnormal pixel values,ensuring that perturbations progress as much as possible in a direction perpendicular to the decision hyperplane in linear problems.This limits anomalies within the perturbations improves their visual stealthiness,and makes them more challenging for defense methods to detect.To verify the effectiveness,stealthiness,and robustness of GN-TUAP,we proposed a comprehensive threat model.Based on this model,extensive experiments were conducted using the CIFAR-10,CIFAR-100,GTSRB,and MNIST datasets,comparing our method with existing state-of-the-art attack methods.We also tested our perturbation triggers using various defense methods and further experimented on the robustness of the triggers against noise filtering techniques.The experimental outcomes demonstrate that backdoor attacks leveraging perturbations generated via our algorithm exhibit cross-model attack effectiveness and superior stealthiness.Furthermore,they possess robust anti-detection capabilities and maintain commendable performance when subjected to noise-filtering methods.展开更多
文摘Medical image segmentation is a powerful and evolving technology in medical diagnosis.In fact,it has been identified as a very effective tool to support and accompany doctors in their fight against the spread of the coronavirus(COVID-19).Various techniques have been utilized for COVID-19 image segmentation,including Multilevel Thresholding(MLT)-based meta-heuristics,which are considered crucial in addressing this issue.However,despite their importance,meta-heuristics have significant limitations.Specifically,the imbalance between exploration and exploitation,as well as premature convergence,can cause the optimization process to become stuck in local optima,resulting in unsatisfactory segmentation results.In this paper,an enhanced War Strategy Chimp Optimization Algorithm(WSChOA)is proposed to address MLT problems.Two strategies are incorporated into the traditional Chimp Optimization Algorithm.Golden update mechanism that provides diversity in the population.Additionally,the attack and defense strategies are incorporated to improve the search space leading to avoiding local optima.The experimental results were conducted by comparing WSChoA with recent and well-known algorithms using various evaluation metrics such as Feature Similarity Index(FSIM),Structural Similarity Index(SSIM),Peak signal-to-Noise Ratio(PSNR),Standard deviation(STD),Freidman Test(FT),and Wilcoxon Sign Rank Test(WSRT).The results obtained by WSChoA surpassed those of other optimization techniques in terms of robustness and accuracy,indicating that it is a powerful tool for image segmentation.
基金funded by National Natural Science Foundation of China under Grant No.61806171The Sichuan University of Science&Engineering Talent Project under Grant No.2021RC15Sichuan University of Science&Engineering Graduate Student Innovation Fund under Grant No.Y2023115,The Scientific Research and Innovation Team Program of Sichuan University of Science and Technology under Grant No.SUSE652A006.
文摘Deep Neural Networks(DNNs)are integral to various aspects of modern life,enhancing work efficiency.Nonethe-less,their susceptibility to diverse attack methods,including backdoor attacks,raises security concerns.We aim to investigate backdoor attack methods for image categorization tasks,to promote the development of DNN towards higher security.Research on backdoor attacks currently faces significant challenges due to the distinct and abnormal data patterns of malicious samples,and the meticulous data screening by developers,hindering practical attack implementation.To overcome these challenges,this study proposes a Gaussian Noise-Targeted Universal Adversarial Perturbation(GN-TUAP)algorithm.This approach restricts the direction of perturbations and normalizes abnormal pixel values,ensuring that perturbations progress as much as possible in a direction perpendicular to the decision hyperplane in linear problems.This limits anomalies within the perturbations improves their visual stealthiness,and makes them more challenging for defense methods to detect.To verify the effectiveness,stealthiness,and robustness of GN-TUAP,we proposed a comprehensive threat model.Based on this model,extensive experiments were conducted using the CIFAR-10,CIFAR-100,GTSRB,and MNIST datasets,comparing our method with existing state-of-the-art attack methods.We also tested our perturbation triggers using various defense methods and further experimented on the robustness of the triggers against noise filtering techniques.The experimental outcomes demonstrate that backdoor attacks leveraging perturbations generated via our algorithm exhibit cross-model attack effectiveness and superior stealthiness.Furthermore,they possess robust anti-detection capabilities and maintain commendable performance when subjected to noise-filtering methods.
