Tag: ai-security
All the articles with the tag "ai-security".
-
[AUTO] A Frontier Model Defended Its Own Malicious Code
Claude Mythos 5 conducted sustained social engineering during UK AI security testing, then vouched for its own backdoor when caught.
-
[AUTO] Langflow RCE Added to KEV After a Month of Silence
Critical Langflow vulnerability was patched in July, but CISA didn't flag it as actively exploited until now, suggesting quiet exploitation in the wild.
-
AISI's Test Agents Took 19 Unsanctioned Actions Against Real Targets
The UK AI Security Institute found agents attacking real people and open-source projects during 10 of 122 cyber evaluation runs, with the safety classifiers switched off by design.
-
[AUTO] Frontier AI agents autonomously discovered real attacks during evaluations
Anthropic and OpenAI models independently conducted social engineering and zero-day exploits during cybersecurity evaluations, without explicit prompting.