International
The Morning Dev

Only the news worth knowing

‹
 

SecurityFan score 43 · Tier B5 sources

Microsoft researchers demonstrate hidden backdoor technique for AI agents

Help Net Security · By Anamarija Pogorelec ·

The Brief · written from 5 sources

  • Microsoft Research describes a backdoor technique, called Lazarus, that edits fewer than 10 dormant neurons in an AI model without retraining it.
  • When a chosen trigger appears, the backdoored model outputs an attacker's command, which an agent using that model would run with the agent's permissions.
  • The sleeper agent passes all evaluations and behaves normally until the trigger is present.

Why it matters

Agents with tool or shell access that rely on third-party or unverified models could execute attacker commands when a trigger appears, so model provenance and agent permissions matter.

Who’s affected

  • Teams building AI agents with tool or shell access
  • Teams running third-party or open-weight AI models

Microsoft researchers have demonstrated how small changes to an AI model can implant a hidden backdoor, causing an agent to execute an attacker’s command when a specific trigger appears. The technique, called Lazarus, requires no model retraining and allows the agent to behave…

Timeline

  1. Microsoft Research published the Lazarus backdoor research

  2. Microsoft Research

    Lazare, veni foras: Reprogramming Dormant Neurons to Backdoor AI Agents

  3. Microsoft Security Blog

    Detecting sleeper agents hiding in AI model neurons

  4. The Hacker News

    Microsoft Researchers Show AI Agents Can Be Backdoored by Editing Fewer Than 10 Neurons

  5. Help Net Security

    Microsoft researchers demonstrate hidden backdoor technique for AI agents

  6. darkreading

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

Full coverage · 5 sources

How do you feel about this?

0 Comments