Monday 16 November
Global

Your region, kept on this device.

Researchers demonstrate Lazarus technique that hides backdoors in AI model neurons

Severity
Medium
Sources
1

Researchers showed that a small change to a few rarely used parts of an AI model can secretly make it issue harmful commands when it sees a specific trigger word. The model behaves normally in everyday tests, so the change is hard to spot. says no criminals have been seen using this method so far.

Like I’m new · Written by AI from 1 source · Wrong?

What to do

  1. Compare every model checkpoint against its declared original before deployment and after updates.
  2. Obtain models only from original publishers, verify published file hashes, and keep approved checkpoints in access-controlled registries.
  3. Restrict AI agent permissions, run code in isolation, limit outbound connections and require human approval for consequential actions.
  4. Monitor agents for suspicious child processes and unexpected network activity.

Written by AI from the sources, checked against them

Full story timeline · 1 update

  1. Wed 11 NovemberClaude Code AI Discovers Technique to Turn Dormant Model Neurons Into Hidden Malware TriggersCyber Security News

Who reported · 1 outlet

Cyber Security News

Who and what is in it

Companies

Products

Report a problem