activity
20232025
most citedSetting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

1 citations · 1 across the 4 of their papers we have counts for

collaborators
Showing cs.LGShow all

1 paper · 1 filter

cs.LG2023★ 1 cited

Setting the Trap: Capturing and Defeating Backdoors in Pretrained Language Models through Honeypots

Ruixiang Tang, Jiayi Yuan, Yiming Li +3

In the field of natural language processing, the prevalent approach involves fine-tuning pretrained language models (PLMs) using local samples. Recent research has exposed the susc…