Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network

Abstract

We question the current evaluation practice on diffusionbased purification methods. Diffusion-based purification methods aim to remove adversarial effects from an input data point at test time. The approach gains increasing attention as an alternative to adversarial training due to the disentangling between training and testing. Well-known white-box attacks are often employed to measure the robustness of the purification. However, it is unknown whether these attacks are the most effective for the diffusion-based purification since the attacks are often tailored for adversarial training. We analyze the current practices and provide a new guideline for measuring the robustness of purification methods against adversarial attacks. Based on our analysis, we further propose a new purification strategy showing competitive results against the state-of-the-art adversarial training approaches.

Kang Won-yong and Ahn Byung-mu’s Dialogue

“…CoLLaVO to further improve once it incorporates a plethora of visual prompts obtained from diverse sources like robust object classification or image captioning models (Lee et al, , 2022Kim et al, 2023c), object-centric causally human-interpretable information (Kim et al, , 2023b, open object detection , visual grounding (Liu et al, 2023d;Ren et al, 2024), interactive or unsupervised segmentation (Kirillov et al, 2023;Kim et al, 2023a), and optical characteristic recognition model (Bautista and Atienza, 2022).…”