Skip to content
MediumNews

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

Published
Record updated
View JSON

Summary

Researchers describe a 'sleeper agent' tactic that hides malicious payloads inside open-weight AI models. The source states that malware can occupy as little as 0.00001% of a neural network, which raises the question of how users could detect it.