Anthropic’s Mythos AI model is known to have remained fairly secretive due to its apparent risk to software systems around the world. And today, a new report says that Mythos was used to expose macOS security vulnerabilities that Apple is currently investigating.
Researchers used Mythos to discover macOS security vulnerabilities
Robert McMillan, writing to The Wall Street Journal:
Security researchers say they have discovered a new way to bypass 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 wrote connects two bugs and a handful of techniques to corrupt Mac memory and then access parts of the device that should be inaccessible.
This is an elevation of privilege exploit, and if chained together with other attacks, it could be used by a hacker to take control of the computer.
McMillan says Apple is currently reviewing the California report to validate its findings. An Apple spokesperson told the WSJ: “Security is our top priority and we take reports of potential vulnerabilities very seriously. »
The California team wrote a 55-page report that they delivered in person to Apple in Cupertino containing their findings.
California CEO Thai Dong said the attack “could not have been carried out by Mythos alone and leveraged the very human cybersecurity expertise of some of the California hackers.”
Details regarding Calif’s findings will be released by the company once the underlying issues have been resolved by Apple. Duong told the WSJ that he thinks the bugs “will probably be fixed fairly quickly.”
You can read more about the Anthropic mythos in our coverage here.
Best Mac accessories
FTC: We use automatic, revenue-generating affiliate links. More.