Tingwei Zhang
Tingwei Zhang
Home
Publications
CV
News
Light
Dark
Automatic
3
Deep-Research Agents Can Be Poisoned via User-Generated Content
Deep-research agents, i.e., systems that rely on multi-agent pipelines to iteratively retrieve, synthesize, and cite Web content in …
Tingwei Zhang
,
Harold Triedman
,
Vitaly Shmatikov
PDF
Cite
Code
Tweet
404 Media
How to Steal Reasoning Without Reasoning Traces
Many large language models (LLMs) use reasoning to generate responses but do not reveal their full reasoning traces (a.k.a. chains of …
Tingwei Zhang
,
John X. Morris
,
Vitaly Shmatikov
PDF
Cite
Code
Tweet
Cite
×