“Very cool! If I understand correctly, this approach can generate steganographic output that is virtually indistinguishable from the output generated by the language model used. Quoting from section 4.3 of the paper: "Most striking, arithmetic coding with the unmodulated language model induces a q distribution with a KL of 4e-8 nats. This indicates that,…”
Neural Linguistic Steganography
Whereas traditional cryptography encrypts a secret message into an unintelligible form, steganography conceals that communication is taking place by encoding a secret message into a cover signal. Language is a particularly pragmatic cover signal due to its benign occurrence and independence from any one medium. Traditionally, linguistic steganography systems encode secret messages in existing text via synonym substitution or word order rearrangements. Advances in neural language models enable previously impractical generation-based techniques. We propose a steganography technique based on arithmetic coding with large-scale neural language models. We find that our approach can generate realistic looking cover sentences as evaluated by humans, while at the same time preserving security by matching the cover message distribution with the language model distribution.
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
推荐在前,同类按时间 · 每篇最多保留 20 条,统计用全部提及“Does anyone know what happened to the live demo on https://github.com/harvardnlp/NeuralSteganography ? It basically does what memespeech is doing, except much better. Both parties would need to agree on a cover text (let's say, a chapter from the NIV Bible). It then generates some text via GPT-2 trained on this cover text, with your hidden message encode…”