Out of Sight.

INFORMATION theory; HUMAN rights violations; MEMES; ONLINE chat

To outside observers, the chat is indistinguishable from any other communication made by the same generative AI: "They might detect that there is AIgenerated content", Schroeder de Witt says, "but they would not be able to tell whether you've encoded secret information into it." In an advance that could benefit spies and dissidents alike, computer scientists have developed a way to communicate confidential information so discreetly that an adversary couldn't even know secrets were being shared. University of Oxford researcher Christian Schroeder de Witt, Carnegie Mellon University researcher Samuel Sokota and their colleagues used an AI program to create innocent-looking chat messages with secret content. [Extracted from the article]

Copyright of Scientific American is the property of Scientific American and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)