Breaking the "Provable Security": Detecting Finite-Precision Artifacts in LLM-based Steganography via Low-Probability Vanishing - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Wenzhao Cao, Yaofei Wang, Donghui Hu. Breaking the "Provable Security": Detecting Finite-Precision Artifacts in LLM-based Steganography via Low-Probability Vanishing. In Maria Liakata, Viviane P. Moreira, Jiajun Zhang 0001, David Jurgens, editors, Findings of the Association for Computational Linguistics, ACL 2026, San Diego, California, United States, July 2-7, 2026. pages 20262-20274, Association for Computational Linguistics, 2026. [doi]

This author has not been identified. Look up 'Wenzhao Cao' in GoogleThis author has not been identified. Look up 'Yaofei Wang' in GoogleThis author has not been identified. Look up 'Donghui Hu' in Google

runs on WebDSL