activity
20242026
collaborators

9 papers

cs.CR2026

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…

cs.LG2026

Learning to Detect Language Model Training Data via Active Reconstruction

Junjie Oscar Yin, John X. Morris, Vitaly Shmatikov +2

Detecting LLM training data is generally framed as a membership inference attack (MIA) problem. However, conventional MIAs operate passively on fixed model weights, using log-likel…

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

Approximating Language Model Training Data from Weights

John X. Morris, Junjie Oscar Yin, Woojeong Kim +2

Modern language models often have open weights but closed training data. We formalize the problem of data approximation from model weights and propose several baselines and metrics…

cs.CL2025

How much do language models memorize?

John X. Morris, Chawin Sitawarin, Chuan Guo +5

We propose a new method for estimating how much a model knows about a datapoint and use it to measure the capacity of modern language models. Prior studies of language model memori…

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…