按年被提到
20222023 · 3 次2026
AI 安全、伦理与社会影响›模型窃取、记忆与水印·arXiv:2210.14889 · cs.CR

Perfectly Secure Steganography Using Minimum Entropy Coupling

Christian Schroeder de Witt, Samuel Sokota, J. Zico Kolter, Jakob Foerster, Martin Strohmeier · 2022
开始阅读 ↗PDFalphaXiv 讨论
被提及 · 3 人首次 2023-03-08 · 最近 2023-05-21
3不同的人
2活跃月份
3讨论串
18被引(OpenAlex)
arXiv 摘要(候选层不写导读)

Steganography is the practice of encoding secret information into innocuous content in such a manner that an adversarial third party would not realize that there is hidden meaning. While this problem has classically been studied in security literature, recent advances in generative models have led to a shared interest among security and machine learning researchers in developing scalable steganography techniques. In this work, we show that a steganography procedure is perfectly secure under Cachin (1998)'s information-theoretic model of steganography if and only if it is induced by a coupling. Furthermore, we show that, among perfectly secure procedures, a procedure maximizes information throughput if and only if it is induced by a minimum entropy coupling. These insights yield what are, to the best of our knowledge, the first steganography algorithms to achieve perfect security guarantees for arbitrary covertext distributions. To provide empirical validation, we compare a minimum entropy coupling-based approach to three modern baselines -- arithmetic coding, Meteor, and adaptive dynamic grouping -- using GPT-2, WaveRNN, and Image Transformer as communication channels. We find that the minimum entropy coupling-based approach achieves superior encoding efficiency, despite its stronger security constraints. In aggregate, these results suggest that it may be natural to view information-theoretic steganography through the lens of minimum entropy coupling.

候选层:至少 2 个不同的人、在 2 个不同月份提到过,还没到主书架的 3 人 3 个月。没有做立场标注,所以只写“被提及”。

HN 书评

没有评论直接链到它;下面是它被提交的讨论串里回复最多的评论(不计入统计)
讨论串评论kurthr · 2023-05

“I think it's the LLM (GPT2) link that makes this interesting to most since it allows relatively high data rate hidden/deniable communication through text interfaces.”

Perfectly Secure Steganography Using Minimum Entropy Coupling原评论 ↗
讨论串评论nullc · 2023-05

“Can someone who understands this work explain why using a range (de)coder to uncompress your ciphertext into the GPT2 generated distribution (in other words the most obvious construction for the case when the sender and receiver have the model) is insufficient to achieve perfect security by their definition?”

Perfectly Secure Steganography Using Minimum Entropy Coupling原评论 ↗
被提交为 story · 3 次