Attention, Please! Adversarial Defense via Activation Rectification and Preservation
This study provides a new understanding of the adversarial attack problem by examining the correlation between adversarial attack and visual attention change. In particular, we observed that: (1) images with incomplete attention regions are more vulnerable to adversarial attacks; and (2) successful adversarial attacks lead to deviated and scattered attention map. Accordingly, an attention-based adversarial defense framework is designed to simultaneously rectify the attention map for prediction and preserve the attention area between adversarial and original images. The problem of adding iteratively attacked samples is also discussed in the context of visual attention change. We hope the attention-related data analysis and defense solution in this study will shed some light on the mechanism behind the adversarial attack and also facilitate future adversarial defense/attack model design.
Code (0)
등록된 구현이 없습니다.
Tasks
Adversarial AttackAdversarial DefenseSimilar Papers 제목 키워드 기반
Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey
Recently, the text-to-image diffusion model has gained considerable attention from the community due to its exceptional image generation capability. A representative model, Stable Diffusion, amassed more than 10 million …
Adversarial AttackImage GenerationSurveyRectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense
Existing defense methods fail to defend against unknown attacks and thus raise generalization issue of adversarial robustness. To remedy this problem, we attempt to delve into some underlying common characteristics among…
Adversarial RobustnessImproving Adversarial Robustness via Channel-wise Activation Suppressing
The study of adversarial examples and their activation has attracted significant attention for secure and robust learning with deep neural networks (DNNs). Different from existing works, in this paper, we highlight two n…
Adversarial RobustnessContrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP
Vision-language models (VLMs) such as CLIP have demonstrated remarkable zero-shot generalization, yet remain highly vulnerable to adversarial examples (AEs). While test-time defenses are promising, existing methods fail …
Zero-shot GeneralizationAdversarial RobustnessAttention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications
Deep neural networks exhibit excellent performance in computer vision tasks, but their vulnerability to real-world adversarial attacks, achieved through physical objects that can corrupt their predictions, raises serious…