Supervisors

Suitable for

Abstract

Steganography is the practice of encoding a plaintext message into another piece of content, called a stegotext, in such a way that an adversary would not realise that hidden communication is occurring. In a recent breakthrough [1,2,3], we showed that messages can be encoded into the output distribution of arbitrary autoregressive neural networks with perfect security [4], i.e. without changing the output distribution, hence rendering the hiding of secret messages information-theoretically undetectable. In this project, we extend perfectly secure steganography to generative AI-models that are not explicitly representable as discrete autoregressive distributions, such as e.g. diffusion models. Such an extension would allow for applying information-theoretic steganography to high-resolution images, potentially resulting in novel tools for investigative journalism and watermarking.

This project is designed to lead to publication. We are looking for a highly-motivated student.

[1] https://arxiv.org/abs/2210.14889

[2] https://www.quantamagazine.org/secret-messages-can-hide-in-ai-generated-media-20230518/

[3] https://www.scientificamerican.com/article/ai-could-smuggle-secret-messages-in-memes/

[4] https://www.sciencedirect.com/science/article/pii/S0890540104000409