Neural Linguistic Steganography · HackerPapers discussions

Neural Linguistic Steganography — mentioned by prophesi

Thu, 12 Mar 2020 17:21:51 GMT

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 encoded in it. You'd then send this generated text to the recipient (which actually looks like a normal message written in the style of your cover text). They'd enter the same chapter of the NIV Bible along with your generated text, which then lets…

Paper and discussion history. A mention is not an endorsement.

Neural Linguistic Steganography — mentioned by cs702

Thu, 05 Sep 2019 22:17:53 GMT

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, consistent with theory (Sallee, 2004), arithmetic coding enables generative steganography matching the exact distribution of the language model used."[a] Regardless of theory, I can't help but think, holy cow, the K-L divergence between the…

Paper and discussion history. A mention is not an endorsement.