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
-
Countering AI Chip Smuggling Has Become a National Security Priority
Reports
Based on the available evidence, artificial intelligence (AI) chip smuggling has likely been occurring at a scale that significantly undermines U.S. attempts to restrict the P...
By Erich Grunewald & Tim Fist
-
How the United States Can Win the Global Tech Race
Commentary
Despite powerful advantages, U.S. success is far from assured....
By Vivek Chilukuri
-
Untangling Ukraine’s “Operation Spiderweb”
Podcast
In this episode, Paul Saunders speaks with Samuel Bendett, an adjunct senior fellow at the Center for a New American Security. Bendett's previous experience includes working f...
By Samuel Bendett
-
Episode 5: War Against Terror – The Predator Age
Podcast
Jack Shanahan, an adjunct senior fellow at the Center for a New American Security, joins the episode to discuss the increasingly prolific arsenal of remotely piloted armed air...
By Lt. Gen. Jack Shanahan
