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

Source: [darkreading](https://www.darkreading.com/vulnerabilities-threats/sleeper-agent-tactic-payloads-open-weight-ai-models) · 2026-11-16 · Security
Page: https://themorning.dev/story/sleeper-agent-tactic-hides-payloads-in-open-weight-ai-models-9c11c754eaec73eb
Kind: security · Impact: medium

## In brief

- A Dark Reading article describes a 'sleeper agent' tactic that hides payloads in open-weight AI models.
- The reported malware can occupy as little as 0.00001% of a neural network.
- The article asks how users can tell such hidden malware is present.

## Why it matters

Developers who download and run open-weight AI models may be running hidden malicious payloads that are hard to detect.

## Coverage

- ['Sleeper Agent' Tactic Hides Payloads in Open-Weight AI Models](https://www.darkreading.com/vulnerabilities-threats/sleeper-agent-tactic-payloads-open-weight-ai-models) — darkreading, 2026-11-16

Tags: ai-security, open-weight-models, malware, supply-chain, machine-learning

---

Brief generated by AI (claude-haiku-5-5) from the reporting listed under Coverage. Headlines belong to their publishers. The Morning Dev – https://themorning.dev
