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
-
Sharper: Trump 2.0
Commentary
Donald Trump's return to the White House is widely expected to reshape America's global priorities. With personnel choices and policy agendas that mark a significant break fro...
By Charles Horn & Gwendolyn Nowaczyk
-
Team America
Podcast
Kate Kuzminski, Deputy Director of Studies, and the Director of the Military, Veterans, and Society (MVS) Program at CNAS, joins to discuss President-elect Donald Trump nomina...
By Katherine L. Kuzminski
-
Response to Request For Comment: “Bolstering Data Center Growth, Resilience, and Security”
Commentary
CNAS experts emphasize the importance of data centers for artificial intelligence...
By Janet Egan, Geoffrey Gertz, Caleb Withers & Grace Park
-
Will Technology Define the Future of Geopolitics?
Rachel Ziemba, Adjunct Senior Fellow at the Center for a New American Security, joins Steve Paikin to discuss the era of growing geopolitical tensions paralleled by deepening ...
By Rachel Ziemba
