most citedDefending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

12 citations · 12 across the 2 of their papers we have counts for

collaborators

2 papers

cs.LG2023★ 12 cited

Defending Pre-trained Language Models as Few-shot Learners against Backdoor Attacks

Zhaohan Xi, Tianyu Du, Changjiang Li +5

Pre-trained language models (PLMs) have demonstrated remarkable performance as few-shot learners. However, their security risks under such settings are largely unexplored. In this…

cs.CR2022

Neural Architectural Backdoors

Ren Pang, Changjiang Li, Zhaohan Xi +2

This paper asks the intriguing question: is it possible to exploit neural architecture search (NAS) as a new attack vector to launch previously improbable attacks? Specifically, we…