# AI security digest for 2026-11-10

Canonical page: https://jonathanglass.cloud/ai-security/2026-11-10.html

Each item is the publisher's title, date, and excerpt.

## Detecting sleeper agents hiding in AI model neurons

- Source: Microsoft Security Blog
- Date: 2026-11-10
- URL: https://www.microsoft.com/en-us/security/blog/2026/11/10/detecting-sleeper-agents-hiding-in-ai-model-neurons/
- Publisher excerpt: 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.

## Cogent and OpenAI build cyber defense factories for enterprises

- Source: OpenAI News
- Date: 2026-11-10
- URL: https://openai.com/index/cogent-security
- Publisher excerpt: Cogent combines OpenAI models with enterprise context to help automatically remediate vulnerabilities with agents.
