Scientists Find Way to Supercharge Dangerous Computer ‘Worms’ With A.I.
The New York Times • • world
Key Points:
- Researchers at the University of Toronto have developed an AI-driven computer worm prototype capable of exploiting any known computer vulnerability and spreading rapidly without human intervention.
- The team tested the worm on an isolated network and deliberately omitted certain technical details from their published paper to prevent misuse by hackers.
- This development raises concerns about AI enabling a new, more dangerous era of cyberattacks that could be harder to defend against than ever before.
- AI company Anthropic has also restricted access to its powerful AI tool, Claude Mythos, to select organizations responsible for critical infrastructure to help patch vulnerabilities before hackers can exploit them.
- The research highlights growing risks to computer networks posed by advances in AI technology, underscoring the need for enhanced cybersecurity measures.