activity
20232026
most citedAdvancing the Robustness of Large Language Models through Self-Denoised Smoothing

4 citations · 7 across the 7 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2023

From Trojan Horses to Castle Walls: Unveiling Bilateral Data Poisoning Effects in Diffusion Models

Zhuoshi Pan, Yuguang Yao, Gaowen Liu +4

While state-of-the-art diffusion models (DMs) excel in image generation, concerns regarding their security persist. Earlier research highlighted DMs' vulnerability to data poisonin…