FU Haoran,WANG Chundong,LIN Hao,HAO Qingbo.Adversarial image detection based on the maximum channel of saliency maps[J].Optoelectronics Letters,2022,(5):307-312 Adversarial image detection based on the maximum channel of saliency maps Author Name Affiliation FU Haoran  Key Laboratory of Computer Vision and System, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China  WANG Chundong  Key Laboratory of Computer Vision and System, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China  LIN Hao  Key Laboratory of Computer Vision and System, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China  HAO Qingbo  Key Laboratory of Computer Vision and System, Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology, Tianjin University of Technology, Tianjin 300384, China  Abstract:       Studies have shown that deep neural networks (DNNs) are vulnerable to adversarial examples (AEs) that induce incorrect 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 detection 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 recognition challenge (ILSVRC) 2012 validation sets. The experimental results show that our method performs well on detecting various AEs. Hits: 341 Download times: 1 View Full Text    Download reader