NeuralSteganography

I first saw this implementation from a Harvard paper back when LLM's were still just a novelty[0]. Glad to see they got their demo site back up. Always thought it was a cool idea. [0] https://github.com/harvardnlp/NeuralSteganography

Thank you for the feedback! Some notes: > The obvious feature gap I see is that it should be possible to provide both the encoder and decoder with a common "context" or prompt to preload the LLM with. There's no option for this in the CLI interface, but you can modify the context in `src/textcoder/coding.py` by changing the `_INITIAL_CONVERSATION` variable. Right now it's configured to ask the LLM to output text in the style of a tweet. > You may want to encode the user's data backwards so that it's easier for users to make arbitrary changes to their message to escape bad covertext output. A random 16-byte value is prepended to each message to serve as the KDF salt and the AES-GCM-SIV nonce. This has the additional benefit that every output is always different, even if they encode the same message. So if the covertext is bad, you can just

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 it recover your hidden message. Basically, memespeech looks like you're hiding something, both to the human eye and to machine learning models. NeuralSteganography solves both of these issues, as it looks like regular human-readable texts to both huma

Cool demo, is the source live? I'd like to see how it works with ipv4-over-twitter. Edit: nevermind, found it. For those looking, it's at https://github.com/harvardnlp/NeuralSteganography