RobustPrompt: Learning to defend against adversarial attacks with adaptive visual prompts

Open Webpage

Chang Liu, Wenzhao Xiang, Yinpeng Dong, Xingxing Zhang, Liyuan Wang, Ranjie Duan, Shibao Zheng, Hang Su

Published: 01 Jan 2025, Last Modified: 04 Oct 2025Pattern Recognit. Lett. 2025EveryoneRevisionsBibTeXCC BY-SA 4.0
Abstract: Highlights•We propose a prompting method to improve robustness on different perturbations.•We aggregate prompts to an adaptive prompt pool.•Experiments show the effectiveness of our method to improve robustness.