STEAD: Robust Provably Secure Linguistic Steganography with Diffusion Language Model

TL;DR

This paper introduces a new linguistic steganography method using diffusion language models, which offers enhanced robustness and security against tampering compared to traditional autoregressive models.

Contribution

The paper proposes a novel steganography approach with diffusion language models, incorporating error correction strategies for improved robustness and provable security.

Findings

The method resists token ambiguity in segmentation.

It withstands insertion, deletion, and substitution attacks.

Theoretical and experimental validation confirms security and robustness.

Abstract

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 a partially parallel manner, allowing us to find robust positions for steganographic embedding that can be combined with error-correcting codes. Furthermore, we introduce 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.