uiuc-backdoor-attack

AI & ML interests

None defined yet.

Recent Activity

qiusizhan  authored a paper about 2 months ago

Removing RLHF Protections in GPT-4 via Fine-Tuning

qiusizhan  authored a paper about 2 months ago

LLM Agents can Autonomously Hack Websites

qiusizhan  authored a paper about 2 months ago

ConFiguRe: Exploring Discourse-level Chinese Figures of Speech

View all activity

Team members 3