MediumNews
'Sleeper Agent' Tactic Hides Payloads in Open-Weight AI Models
- Published
- Record updated
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.
Related items
- HighGHSA-8vf2-hxg5-crqh: Kubeshark: MCP `start_kubeshark` argument injection via `pod_regex` → image redirect → cluster takeoverSimilar attack · GitHub Advisory Database
- MediumCursor Supply Chain Attack Started at Fireworks AISimilar attack · SecurityWeek
- MediumAmazon Uncovers AI Agent Campaign Targeting LiteLLM, Dify, and Other Apps for API KeysSimilar attack · The Hacker News
- MediumCursor Says Stolen Fireworks AI Key Led to Trojanized Claude Code Extension IncidentSimilar attack · The Hacker News
- MediumCursor confirms security breach led to malicious Claude Code extensionSimilar attack · BleepingComputer