1 citations · 1 across the 6 of their papers we have counts for
8 papers
Speculative Probing: LLM Monitoring at Speculative-Decoding Cost
Collin Zhang, Tingwei Zhang, Vitaly Shmatikov
Real-time classification during language model inference is valuable for safety filtering, behavioral analysis, and model monitoring, but current approaches force a trade-off betwe…
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…
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…
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…
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…
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…
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…
Extracting Prompts by Inverting LLM Outputs
Collin Zhang, John X. Morris, Vitaly Shmatikov
We consider the problem of language model inversion: given outputs of a language model, we seek to extract the prompt that generated these outputs. We develop a new black-box metho…