April 20, 2023
Hijacked AI Assistants Can Now Hack Your Data
In February, a team of cybersecurity researchers successfully cajoled a popular AI assistant into trying to extract sensitive data from unsuspecting users by convincing it to adopt a “data pirate” persona. The AI’s “ahoy’s” and “matey’s” in pursuit of personal details were humorous, but the implications for the future of cybersecurity are not: The researchers have provided proof of concept for a future of rogue hacking AIs.
Early adopters of powerful new AI tools should recognize that they are subjects of a large-scale experiment with a new kind of cyberattack.
Building on OpenAI’s viral launch of ChatGPT, a range of companies are now empowering their AI assistants with new abilities to browse the internet and interact with online services. But potential users of these powerful new aides need to carefully weigh how they balance the benefits of cutting-edge AI agents with the fact that they can be made to turn on their users with relative ease.
Read the full article from The Hill.
More from CNAS
-
CNAS Insights
Technology & National Security
CNAS Insights | Governing Jailbreak IncidentsIn June 2026, Anthropic publicly released Claude Fable 5, a restricted version of its highly cyber-capable Mythos model. Within days, reports reached U.S. officials that resea...
By Ben Hayum
-
Commentary
Technology & National Security
Closing the Remote Access LoopThis article was originally published in Issues in Science and Technology. As Asad Ramzanali argues in “Why the Cloud Needs Competition” (Issues, Winter 2026), cloud computing...
By Michelle Nie
-
Commentary
Technology & National Security
Losing the War of the FutureThis article was originally published in Foreign Affairs. In its recent campaign against Iran, the United States dominated the skies using its traditional airpower. The U.S. m...
By Paul Scharre
-
Podcast
Technology & National Security
We Need AI Treaties. This Is How We Get ThemIn this episode, Tristan sits down with two experts in this field to discuss the kinds of verification technology we need for AI, the challenges of building it, and the world ...
By Janet Egan & Tim Fist
