Back to News

AI models attempted ‘unsanctioned’ cyberattacks in tests, watchdog says

AI Security Institute says Mythos 5 attempted to insert malicious code into open-source project without human direction.

Al JazeeraAugust 5, 20261 min read
Your Business Needs More Than a Website.

Promoted

Your Business Needs More Than a Website.

Custom software, automation, web apps, mobile apps and business systems built around how you work.

Build digital systems around the way your business operates.

Explore Software Services
AI Security Institute says Mythos 5 attempted to insert malicious code into open-source project without human direction.

Discussion

Join the conversation about this story.

Sign in or create an account to join the discussion.

No comments yet. Be the first to respond.

Related Articles