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's First 100 Days
Donald Trump takes office in a complex and volatile global environment. Rising tensions with China, the continued war in Ukraine, and instability in the Middle East all pose s...
By Charles Horn
-
Accelerate America’s Quantum Technology Leadership
As the U.S.-China competition for quantum technology leadership continues to intensify, the Trump administration should prioritize both advancing and protecting the country’s ...
By Constanza M. Vidal Bustamante
-
Secure America’s Tech Competitiveness
The Trump administration must bolster America’s science, technology, engineering, and mathematics (STEM) workforce and broader technological competitiveness—documented shortag...
By Sam Howell
-
Make America the Biopower
No country has a better biotechnology hand than America. The administration has a historic opportunity to play it wisely and secure the United States’ position as the 21st cen...
By Vivek Chilukuri