collaborators

6 papers

cs.CR2026

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…

cs.LG2026

Harnessing the Universal Geometry of Embeddings

Rishi Jha, Collin Zhang, Vitaly Shmatikov +1

We introduce the first method for translating text embeddings from one vector space to another without any paired data, encoders, or predefined sets of matches. Our unsupervised ap…

cs.CL2025

Language Confusion Gate: Language-Aware Decoding Through Model Self-Distillation

Collin Zhang, Fei Huang, Chenhan Yuan +1

Large language models (LLMs) often experience language confusion, which is the unintended mixing of languages during text generation. Current solutions to this problem either neces…

cs.CR2025

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…

cs.CL2025

Universal Zero-shot Embedding Inversion

Collin Zhang, John X. Morris, Vitaly Shmatikov

Embedding inversion, i.e., reconstructing text given its embedding and black-box access to the embedding encoder, is a fundamental problem in both NLP and security. From the NLP pe…

cs.CL2025

Adversarial Decoding: Generating Readable Documents for Adversarial Objectives

Collin Zhang, Tingwei Zhang, Vitaly Shmatikov

We design, implement, and evaluate adversarial decoding, a new, generic text generation technique that produces readable documents for different adversarial objectives. Prior metho…