Details

Autor(en) / Beteiligte

• Kaptchuk, Gabriel
• Jois, Tushar M.
• Green, Matthew
• Rubin, Aviel D.

Titel

Meteor: Cryptographically Secure Steganography for Realistic Distributions

Ist Teil von

• Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security, 2021, p.1529-1548

Ort / Verlag

New York, NY, USA: ACM

Erscheinungsjahr

2021

Quelle

ACM Digital Library

Beschreibungen/Notizen

• Despite a long history of research and wide-spread applications to censorship resistant systems, practical steganographic systems capable of embedding messages into realistic communication distributions, like text, do not exist. We identify two primary impediments to deploying universal steganography: (1) prior work leaves the difficult problem of finding samplers for non-trivial distributions unaddressed, and (2) prior constructions have impractical minimum entropy requirements. We investigate using generative models as steganographic samplers, as they represent the best known technique for approximating human communication. Additionally, we study methods to overcome the entropy requirement, including evaluating existing techniques and designing a new steganographic protocol, called Meteor. The resulting protocols are provably indistinguishable from honest model output and represent an important step towards practical steganographic communication for mundane communication channels. We implement Meteor and evaluate it on multiple computation environments with multiple generative models.