paper-with-me

홈 › Papers

Attention, Please! Adversarial Defense via Activation Rectification and Preservation

2018-11-24 · Shangxi Wu, Jitao Sang, Kaiyuan Xu, Jiaming Zhang, Jian Yu

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.

📄 PDF Abstract BibTeX arXiv:1811.09831

Code (0)

등록된 구현이 없습니다.

Tasks

Adversarial AttackAdversarial Defense

Similar Papers 제목 키워드 기반

Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Survey

2024-07-10 · Chenyu Zhang, Mingwang Hu, Wenhui Li, Lanjun Wang

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 GenerationSurvey

Rectifying Adversarial Sample with Low Entropy Prior for Test-Time Defense

2025-07-04 · Lina Ma, Xiaowei Fu, Fuxiang Huang, Xinbo Gao 외

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 Robustness

Improving Adversarial Robustness via Channel-wise Activation Suppressing

2021-03-11 · ICLR 2021 1 · Yang Bai, Yuyuan Zeng, Yong Jiang, Shu-Tao Xia 외

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 Robustness

Contrastive Spectral Rectification: Test-Time Defense towards Zero-shot Adversarial Robustness of CLIP

2026-01-27 · Sen Nie, Jie Zhang, Zhuo Wang, Shiguang Shan 외 arxiv

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 Robustness

Attention-Based Real-Time Defenses for Physical Adversarial Attacks in Vision Applications

2023-11-19 · Giulio Rossolini, Alessandro Biondi, Giorgio Buttazzo

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…