Image credit: Yuichiro Chino/Getty
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
China Is Flirting With AI Catastrophe
Today’s AI sprint would not be the first time Beijing’s desire to hasten progress invited disaster....
By Bill Drexel & Hannah Kelley
An AI Challenge: Balancing Open and Closed Systems
Navigating the spectrum between open and closed is critical to effective artificial intelligence policy. The right balance will promote innovation and competition while managi...
By Pablo Chavez
Autonomous F-16 fighter jets being tested by the U.S. military
The U.S. military is testing an autonomous F-16 fighter jet that can make combat safer for American soldiers. In simulations, the AI already outflies trained human pilots. Her...
By Paul Scharre
Congress ponders regulation of powerful emergent A.I. platforms
Can Congress keep up with the pace of growth in artificial intelligence? Paul Scharre of the Center for a New American Security talks about the current attempts to regulate A....
By Paul Scharre