Steganography in a language model's word choices

Hide a short message in text generated by a local model, by steering which of the top-k tokens it picks. The text must read naturally; the recipient with the same model must recover the message.

Requirements

Encoder: given a secret (up to 32 bytes) and a prompt, generate fluent text that encodes it in token choices

Decoder: given the text and the same model and prompt, recover the secret exactly

Round-trip tests on ten messages

The encoded text must pass a simple perplexity check against unencoded text from the same prompt

Document the bandwidth (bits per token) you achieve

Technical Notes

Any local model with logit access. Determinism matters — pin the seed and the sampling.

llmcryptographypythonlocal-ai

Expert

View on GitHub

GoShip's MCP server tracks how you interact with AI — not your code. Connect it to get scored and improve your workflow.

Discussion (0)

No comments yet

Be the first to share your thoughts on this challenge.