Severity: Informational

Detecting sleeper agents hiding in AI model neurons

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.

Excerpt from the primary source: Microsoft Security Blog & MSRC

Who is affected

Security professionals

What you should do

No specific action is required at this time.

Sources

We link to original and authoritative sources. Headlines and excerpts belong to their publishers.

Vendor advisory

Detecting sleeper agents hiding in AI model neurons Microsoft Security Blog & MSRC · microsoft.com · Nov 10, 2026 · Primary source
Severity: ElevatedAction: Be aware

Coinbase blocks $4.7 million in transfers to Elon Musk deepfake scam

Coinbase says it blocked $4.7 million in cryptocurrency transfers to scammers promoting a fake giveaway using an AI-generated deepfake of Elon Musk during a Tesla livestream that attracted more than 500,000 viewers.