Detecting sleeper agents hiding in AI model neurons

Microsoft Security Blog · 2026-11-10

Microsoft Research has released new threat research detailing how a capable agent model could be turned into a sleeper agent by editing fewer than ten neurons to inject a short payload; Microsoft Research has also found that this threat is detectable by frontier agents, which can identify anomalous weight edits. The post Detecting sleeper agents hiding in AI model neurons appeared first on Microsoft Security Blog.

Source

Cogent and OpenAI build cyber defense factories for enterprises

OpenAI News · 2026-11-10

Cogent combines OpenAI models with enterprise context to help automatically remediate vulnerabilities with agents.

Source