activity
20222026
most citedTrojLLM: A Black-box Trojan Prompt Attack on Large Language Models

12 citations · 23 across the 25 of their papers we have counts for

collaborators
Showing cs.CVShow all

1 paper · 1 filter

cs.CV2022

ESTAS: Effective and Stable Trojan Attacks in Self-supervised Encoders with One Target Unlabelled Sample

Jiaqi Xue, Qian Lou

Emerging self-supervised learning (SSL) has become a popular image representation encoding method to obviate the reliance on labeled data and learn rich representations from large-…