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

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	He, Bowei, Yin, Lihao, Zhen, Hui-Ling, Zhang, Jianping, Hong, Lanqing, Yuan, Mingxuan, Ma, Chen
Format:	Preprint
Published:	2025
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.06892