Xirui Li | University of California, Los Angeles

About Me

I am a 2nd-year Master student at UCLA.

I am currently a member of ARC, an AIGC Research Collaboration based off several labs to pursue targeted topics in Multimodal Language Agents, advised by Ruochen Wang and Prof. Cho-Jui Hsieh. My research currently focuses on Attacks on Large Language Models. Prior to the era of LLM, I worked on object detection and visual interpretations. Besides research, I am also interested in entrepreneurial opportunities.

I obtained my B.S. degree in Electrical and Computer Engineering from the Technical University of Munich. During this period, I did my thesis about object detection at fortiss, a research institute of the Free State of Bavaria for software-intensive systems.

Research Interests

Computer Vision: object detection, visual interpretations
Language Agents: attack on LLMs, multimodal agents

News

[Feb. 2024] Our paper about attack on LLMs is preprinted on ArXiv.

Publications

Arxiv

DrAttack: Prompt Decomposition and Reconstruction Makes Powerful LLM Jailbreakers

Xirui Li, Ruochen Wang, Minhao Cheng, Tianyi Zhou, Cho-Jui Hsieh

(Arxiv), 2024.

ARC group present, Under Review