STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model

Yuang Qi (University of Science and Technology of China) · Na Zhao (Singapore University of Technology and Design) · Qiyi Yao (University of Science and Technology of China) · Benlong Wu (University of Science and Technology of China) · Weiming Zhang (University of Science and Technology of China) · Nenghai Yu (University of Science and Technology of China) · Kejiang Chen (University of Science and Technology of China)

active tampering attackautoregressive language models diffusion language models error propagationerror-correcting codesinsertion deletion substitutionneighborhood search correctionpartial parallel generationprovably secure linguistic steganographypseudo-random error correctionsteganographic embeddingsteganographic extractionstegotext segmentationtoken ambiguitytoken-level attacks

Recent provably secure linguistic steganography (PSLS) methods rely on mainstream autoregressive language models (ARMs) to address historically challenging tasks, that is, to disguise covert communication as ``innocuous'' natural language communication. However, due to the characteristic of sequential generation of ARMs, the stegotext generated by ARM-based PSLS methods will produce serious error propagation once it changes, making existing methods unavailable under an active tampering attack. To address this, we propose a robust provably secure linguistic steganography with diffusion language models (DLMs). Unlike ARMs, DLMs can generate text in partial parallel manner, allowing us to find robust positions for steganographic embedding that can be combined with error-correcting codes. Furthermore, we introduce an error correction strategies, including pseudo-random error correction and neighborhood search correction, during steganographic extraction. Theoretical proof and experimental results demonstrate that our method is secure and robust. It can resist token ambiguity in stegotext segmentation and, to some extent, withstand token-level attacks of insertion, deletion, and substitution.