Anthropic's Mythos AI can spot flaws in almost every computer on Earth. Uh-oh.
ATT&CK techniques detected
T1598Phishing for Information
45%
"so - called phishing attacks aimed at prying loose confidential information, said zach lewis, the chief information officer at the university of health sciences and pharmacy in st. louis. " it ' s been used to really script those dialogues, those conversations, those phishing ema…"
Which technique(s) should be tagged here? Pick zero or more — leaving blank just records that the original was wrong.
No matches for .
Loading techniques…
T1588.006Vulnerabilities
43%
"hackers already have access to advanced ai models and are using them for a range of malign purposes, including to create autonomous " agents " capable of carrying out attacks without human intervention. such attacks range from spreading malware and executing identity theft scams …"
Which technique(s) should be tagged here? Pick zero or more — leaving blank just records that the original was wrong.
No matches for .
Loading techniques…
Summary
Could powerful AI models like Anthropic's Mythos give cybercriminals and other bad actors a roadmap for exploiting tech systems?