CRCLMar 26, 2024

Provably Secure Disambiguating Neural Linguistic Steganography

arXiv:2403.17524v213 citationsh-index: 20IEEE Transactions on Dependable and Secure Computing
Originality Incremental advance
AI Analysis

This addresses a critical reliability and security issue in neural linguistic steganography for secure communication, though it is incremental as it builds on existing provably secure methods.

The paper tackles the segmentation ambiguity problem in neural linguistic steganography, which causes decoding failures, by proposing SyncPool, a secure disambiguation method that groups tokens with prefix relationships and uses a CSPRNG for synchronization, enabling provably secure steganography without altering token distributions.

Recent research in provably secure neural linguistic steganography has overlooked a crucial aspect: the sender must detokenize stegotexts to avoid raising suspicion from the eavesdropper. The segmentation ambiguity problem, which arises when using language models based on subwords, leads to occasional decoding failures in all neural language steganography implementations based on these models. Current solutions to this issue involve altering the probability distribution of candidate words, rendering them incompatible with provably secure steganography. We propose a novel secure disambiguation method named SyncPool, which effectively addresses the segmentation ambiguity problem. We group all tokens with prefix relationships in the candidate pool before the steganographic embedding algorithm runs to eliminate uncertainty among ambiguous tokens. To enable the receiver to synchronize the sampling process of the sender, a shared cryptographically-secure pseudorandom number generator (CSPRNG) is deployed to select a token from the ambiguity pool. SyncPool does not change the size of the candidate pool or the distribution of tokens and thus is applicable to provably secure language steganography methods. We provide theoretical proofs and experimentally demonstrate the applicability of our solution to various languages and models, showing its potential to significantly improve the reliability and security of neural linguistic steganography systems.

Code Implementations1 repo
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes