Addressing Segmentation Ambiguity in Neural Linguistic Steganography
TL
TL;DR
This paper demonstrates that segmentation ambiguity indeed causes occasional decoding failures at the receiver’s side, and proposes simple tricks to overcome this problem, which are even applicable to languages without explicit word boundaries.
Abstract
Previous studies on neural linguistic steganography, except Ueoka et al. (2021), overlook the fact that the sender must detokenize cover texts to avoid arousing the eavesdropper’s suspicion. In this paper, we demonstrate that segmentation ambiguity indeed causes occasional decoding failures at the receiver’s side. With the near-ubiquity of subwords, this problem now affects any language. We propose simple tricks to overcome this problem, which are even applicable to languages without explicit word boundaries.
References34 items
1
Generative Steganography Based on Long Readable Text Generation
2
Autoregressive Linguistic Steganography Based on BERT and Consistency Coding
3
Semantic-Preserving Linguistic Steganography by Pivot Translation and Semantic-Aware Bins Coding
4
Provably Secure Generative Linguistic Steganography
5