Meta joins OpenAI, Anthropic in latest AI test breach
Meta has become the third frontier AI developer in recent weeks to disclose a security incident involving one of its advanced AI models during cyber capability testing conducted by AI safety startup, Irregular, placing the independent evaluator at the center of a series of disclosures involving the industry’s leading A…
Short extract only — this publisher licenses its text. Read the full release at the source.
More from CSO Online
- F5 fixes actively exploited zero-day flaw in BIG-IP APM
- GitHub App keys can still enable takeovers long after they are forgotten
- Okta bets on identity to control AI agents, but is identity enough?
The rest of this wire is for subscribers
Every release from this source, the moment it crosses — plus 80+ other newswires, saved searches and instant alerts.
7 days, no card required.
Read releases like this the second they cross the wire.
1,400+ feeds — live on PPN World right now. Every release from this source, the moment it crosses — plus 80+ other newswires, saved searches and instant alerts.
Start the free trial →Your announcement next? Distribute your press release to the global wires with PPN Source — and track its pickup live here.
PPN Source →