典型文献
Adversarial image detection based on the maximum channel of saliency maps
文献摘要：
Studies have shown that deep neural networks(DNNs)are vulnerable to adversarial examples(AEs)that induce in-correct behaviors.To defend these AEs,various detection techniques have been developed.However,most of them only appear to be effective against specific AEs and cannot generalize well to different AEs.We propose a new detec-tion method against AEs based on the maximum channel of saliency maps(MCSM).The proposed method can alter the structure of adversarial perturbations and preserve the statistical properties of images at the same time.We conduct a complete evaluation on AEs generated by 6 prominent adversarial attacks on the ImageNet large scale visual recog-nition challenge(ILSVRC)2012 validation sets.The experimental results show that our method performs well on de-tecting various AEs.
文献关键词：
中图分类号：
作者姓名：
FU Haoran;WANG Chundong;LIN Hao;HAO Qingbo
作者机构：
Key Laboratory of Computer Vision and System,Tianjin Key Laboratory of Intelligence Computing and Novel Soft-ware Technology,Tianjin University of Technology,Tianjin 300384,China
文献出处：
引用格式：
[1]FU Haoran;WANG Chundong;LIN Hao;HAO Qingbo-.Adversarial image detection based on the maximum channel of saliency maps)[J].光电子快报（英文版）,2022(05):307-312
A类：
ILSVRC
B类：
Adversarial,detection,maximum,channel,saliency,maps,Studies,have,shown,that,deep,neural,networks,DNNs,are,vulnerable,adversarial,examples,AEs,induce,correct,behaviors,To,defend,these,various,techniques,been,developed,However,most,them,only,appear,effective,against,specific,cannot,generalize,well,different,We,new,method,MCSM,proposed,alter,structure,perturbations,preserve,statistical,properties,images,same,conduct,complete,evaluation,generated,by,prominent,attacks,ImageNet,large,scale,visual,recog,nition,challenge,validation,sets,experimental,results,our,performs,tecting
AB值：
0.618372
相似文献
机标中图分类号，由域田数据科技根据网络公开资料自动分析生成，仅供学习研究参考。
