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
-
Tariffs and Tech: An Uncertain Recipe
Commentary
Higher tariffs could prompt American cloud companies to shift more of their capital investments abroad....
By Pablo Chavez
-
Lessons in Learning
Reports
Executive Summary Although claims of a revolution in military affairs may be overhyped, the potential for artificial intelligence (AI) and autonomy to change warfare is growin...
By Josh Wallin
-
Human, Machine, War: How the Mind-Tech Nexus Will Win Future Wars
Air University Press has published Strategic Multilayer Assessment’s (SMA) latest book, Human, Machine, War: How the Mind-Tech Nexus Will Win Future Wars. Forewords by General...
By Samuel Bendett & Lt. Gen. Jack Shanahan
-
Five Objectives to Guide U.S. AI Diffusion
Commentary
The Framework for AI Diffusion (the Framework) is an ambitious proposal to shape the global distribution of critical AI capabilities, maintain U.S. AI leadership, and prevent ...
By Janet Egan & Spencer Michaels
