AW AgentAIWatchPublic threat intelligence
Public sources only

INCIDENT REPORT

'Sleeper Agent' Tactic Hides Payloads in Open-Weight AI Models

2026-11-16
unverified public report Unknown Unknown

Malware can lurk inside just 0.00001% of a neural network. How, then, can any user tell it's there?

Risk rationale: model (+5) Source: darkreading.com ↗
23Risk
24Confidence

← All incident reports