Guowen Xu
3 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper investigates how various fine-tuning methods can be used both to intentionally misalign and subsequently realign large language models (LLMs), revealing distinct strengths for attack and defense mechanisms.
This paper presents the first systematic study of black-box skill stealing attacks against proprietary LLM agents, demonstrating that structured agent skills can be easily extracted, posing a significant and often overlooked copyright risk.
This paper proposes a method to induce fragmented generation in large language models to increase inference cost without degrading model utility.
Papers
FragToken: Amplifying LLM Inference Costs through Noncanonical Token Generation
Zihan Wang, Rui Zhang, Xinyuan Qian, Qingchuan Zhao +2 more
This paper proposes a method to induce fragmented generation in large language models to increase inference cost without degrading model utility.