Provably Secure Disambiguating Neural Linguistic Steganography

arXiv:2403.17524v1 Announce Type: new
Abstract: 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 …

arxiv aspect cs.cl cs.cr decoding failures language language models linguistic problem research segmentation steganography