Search Results for author: Yukai Zhou

Found 1 papers, 0 papers with code

Don't Say No: Jailbreaking LLM by Suppressing Refusal

no code implementations25 Apr 2024 Yukai Zhou, Wenjie Wang

However, the typical attack in this category GCG has very limited attack success rate.

Natural Language Inference

Cannot find the paper you are looking for? You can Submit a new open access paper.