1 citations · 2 across the 5 of their papers we have counts for
4 papers · 1 filter
How to Steal Reasoning Without Reasoning Traces
Tingwei Zhang, John X. Morris, Vitaly Shmatikov
Many large language models (LLMs) use reasoning to generate responses but do not reveal their full reasoning traces (a.k.a. chains of thought), instead outputting only final answer…
Adversarial Hubness in Multi-Modal Retrieval
Tingwei Zhang, Fnu Suya, Rishi Jha +2
Hubness is a phenomenon in high-dimensional vector spaces where a point from the natural distribution is unusually close to many other points. This is a well-known problem in infor…
Self-interpreting Adversarial Images
Tingwei Zhang, Collin Zhang, John X. Morris +2
We introduce a new type of indirect, cross-modal injection attacks against visual language models that enable creation of self-interpreting images. These images contain hidden "met…
Adversarial Illusions in Multi-Modal Embeddings
Tingwei Zhang, Rishi Jha, Eugene Bagdasaryan +1
Multi-modal embeddings encode texts, images, thermal images, sounds, and videos into a single embedding space, aligning representations across different modalities (e.g., associate…