Posted on Leave a comment

Researchers have achieved a breakthrough to enable ‘perfectly secure’ hidden communications for the first time.

Spectrogram of a hidden image encoded as sound in a song

A group of researchers has made a breakthrough in secure communications by developing an algorithm that conceals sensitive information so effectively that it is impossible to detect that anything has been hidden. The algorithm uses steganography: a method of hiding sensitive information inside innocuous content. Steganography differs from cryptography because the sensitive information is concealed in such a way that it obscures the fact that something has been hidden. For example, hiding a Shakespeare poem inside an AI-generated image of a cat or a picture of a demon inside an audio track.

Despite having been studied for more than 25 years, existing steganography approaches generally have imperfect security, meaning that individuals who use these methods risk being detected. This is because previous steganography algorithms subtly change the distribution of the innocuous content.

To overcome this, the research team used recent breakthroughs in information theory, specifically minimum entropy coupling, which allows one to join two distributions of data together so that their mutual information is maximized, but the individual distributions are preserved. As a result, with the new algorithm, there is no statistical difference between the distribution of the innocuous content and the distribution of content that encodes sensitive information.

The algorithm was tested using several types of models that produce auto-generated content, such as GPT-2, an open-source language model, and WAVE-RNN, a text-to-speech converter. Besides being perfectly secure, the new algorithm showed up to 40% higher encoding efficiency than previous steganography methods across a variety of applications, enabling more information to be concealed within a given amount of data. This may make steganography an attractive method even if perfect security is not required, due to the benefits for data compression and storage.

The research team has filed a patent for the algorithm but intend to issue it under a free license to third parties for non-commercial responsible use. The work has been published as a preprint paper on arXiv, as well as an open-sourced inefficient implementation of their method on Github. They will also present the new algorithm at the premier AI conference, the 2023 International Conference on Learning Representations in May.

Co-lead author Dr Christian Schroeder de Witt (Department of Engineering Science, University of Oxford) said:

“Our method can be applied to any software that automatically generates content, for instance probabilistic video filters, or meme generators. This could be very valuable, for instance, for journalists and aid workers in countries where the act of encryption is illegal. However, users still need to exercise precaution as any encryption technique may be vulnerable to side-channel attacks such as detecting a steganography app on the user’s phone.”

Image Credits

In-Article Image Credits

Spectrogram of a hidden image encoded as sound in a song via Wikimedia Commons with usage type - Creative Commons License. April 20, 2008

Featured Image Credit

Spectrogram of a hidden image encoded as sound in a song via Wikimedia Commons with usage type - Creative Commons License. April 20, 2008

 

Leave a Reply

Your email address will not be published. Required fields are marked *