Anthropic’s Mythos AI model has famously been kept fairly secret due to the obvious risks to software systems around the world. And today, a new report says Mythos was used to expose a security vulnerability in macOS that Apple is currently investigating.
Researchers used Mythos to discover security vulnerabilities in macOS
Robert Macmillan, writing: wall street journal:
Security researchers said they have discovered a new way to circumvent Apple’s cutting-edge security technology using techniques they discovered while testing an early version of Anthropic’s Mythos AI software in April.
Researchers at Calif, a Palo Alto-based security research firm, say the software they created combined two bugs and several techniques to corrupt Mac memory and gain access to parts of the device that should be inaccessible.
This is a so-called privilege escalation exploit that, when chained with other attacks, can be used by hackers to take control of your computer.
McMillan said Apple is currently reviewing the report from California and verifying its findings. This was announced by an Apple spokesperson. WSJ: “Security is our top priority and we take reports of potential vulnerabilities very seriously.”
The California team compiled a 55-page report containing their findings and delivered it directly to Apple in Cupertino.
Tai Dong, California’s chief executive, said the attack “couldn’t have been done by Mythos alone and without leveraging the very human cybersecurity expertise of several California hackers.”
Details about Calif’s discovery will be released by Apple once the underlying issue is resolved by the company. Duong told the Journal that he believes the bug will “probably be fixed fairly quickly.”
You can read more about Anthropic’s Mythos in this article.
best mac accessories
(Tag to translate) Anthropology
