Illustration credit: Christian Schroeder de Witt.
Images sourced from Hippo.px and Flickr
Researchers have achieved 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
A team lead by University of Oxford researchers has achieved 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.
Working in close collaboration with Carnegie Mellon University, the researchers developed a new method which they envisage may soon be used widely in digital human communications, including social media and private messaging. In particular, the ability to send perfectly secure information may empower vulnerable groups, such as dissidents, investigative journalists, and humanitarian aid workers.
The algorithm applies to a setting called steganography: the practice of hiding sensitive information inside of innocuous content. Steganography differs from cryptography because the sensitive information is concealed in such a way that this obscures the fact that something has been hidden. An example could be hiding a Shakespeare poem inside an AI-generated image of a cat.
“This breakthrough in secure communications promises unprecedented levels of security and efficiency to its users, who may enjoy a much higher extent of plausible deniability than with previous steganographic methods. We will be working with all relevant communities of stakeholders, including humanitarian aid workers and investigative journalists, to unlock its potential in the real world.”
Dr Christian Schroeder de Witt
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 would 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 such that their mutual information is maximised, 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 licence to third parties for non-commercial responsible use. This includes academic and humanitarian use, and trusted third-party security audits. The researchers have published this work as a preprint paper on arXiv, as well as open-sourced an 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.
AI-generated content is increasingly used in ordinary human communications, fuelled by products such as ChatGPT, Snapchat AI-stickers, and TikTok video filters. As a result, steganography may become more widespread as the mere presence of AI-generated content will cease to arouse suspicion.
Co-lead author Dr Christian Schroeder de Witt, pictured left, says, “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.”
Contributing author Professor Jakob Foerster says, “This paper is a great example of research into the foundations of machine learning that leads to breakthrough discoveries for crucial application areas. It’s wonderful to see that Oxford, and our young lab in particular, is at the forefront of it all.”
Original Article: New breakthrough enables perfectly secure digital communications
More from: University of Oxford | Carnegie Mellon University
The Latest Updates from Bing News
Go deeper with Bing News on:
Secure digital communications
- Unlocking Secure Collaboration: Best Practices for Large File Sharing in Client Portals
Ensuring Efficiency and Confidentiality in Client Communication In today's digital landscape, secure collaboration is ...
- The ultimate free digital security guide: Stay safe without spending a dime
Two-factor authentication, also known as two-step authentication, is an important tool for keeping your accounts safe — even if you use a password manager. If an attacker gets your password somehow, ...
- Corero Network Security and SEMPRE Launch Partnership To Secure the Availability of Critical Infrastructure
Carl Herberger, CEO of Corero Network Security, commented, "We are excited to team with SEMPRE to advance the availability of secure and resilient networks. Our joint research will integrate our ...
- The future of online communication: Secure and censorship-resistant chat on blockchain
Communication remains a basic necessity no matter how much humanity moves forward. The digital era has brought a myriad of online tools that bring people together, and it was a rather swift transition ...
- Special Aerospace Services buys secure communications business
Godspeed Capital Management has now backed two acquisitions of SAS with this newest move also adding a NASA footprint.
Go deeper with Bing News on:
Minimum entropy coupling
- Information-entropy enabled identifying topological photonic phase in real space
Researchers led by Prof. Xiaoyong Hu at Peking University, China, are interested in topological photonics. They have proposed an interdisciplinary approach to study the topological systems through ...
- 2024 Minimum Wage Changes: Everything You Need To Know
Katherine Haan is a small business owner with nearly two decades of experience helping other business owners increase their incomes. With over a decade of editorial experience, Rob Watts breaks ...
- The Minimum Payment on Your Credit Card Debt Might Not Be Enough: Here's Why
You might dodge fees and penalties by making minimum payments, but it'll take you longer to get out of credit card debt. Katie is a writer covering all things how-to at CNET, with a focus on ...
- 20 cities & 15 states with the highest minimum wages in 2024
The federal minimum wage has been $7.25 since 2009, but many states and cities have higher minimum wages. In any given place, the highest applicable minimum wage (between federal, state, and city ...
- New method to measure entropy production on the nanoscale
A computational model for entropy "If we turn to how entropy is formed in devices, they all need to be turned on and off, or need to move something from A to B. As a consequence, entropy is ...