Certifying Language Model Robustness with Fuzzed Randomized Smoothing: An Efficient Defense Against Backdoor Attacks

Open Webpage

Bowei He, Lihao Yin, Hui-Ling Zhen, Jianping Zhang, Lanqing Hong, Mingxuan Yuan, Chen Ma

Published: 01 Jan 2025, Last Modified: 31 Jul 2025ICLR 2025EveryoneRevisionsBibTeXCC BY-SA 4.0