Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Microsoft’s Lazarus backdoors AI agents with fewer than 10 neurons

AI summary

Microsoft researchers demonstrated Lazarus, a technique that reprograms fewer than 10 dormant neurons to implant a trigger-activated backdoor in an LLM-based agent without retraining it. In the reported demonstration, the agent behaved normally and passed standard evaluations until a trigger caused it to download and execute attacker-supplied code. Microsoft says reliable detection requires comparison with unmodified weights and recommends model provenance checks, weight auditing, permission restrictions, and monitoring.

In-depth insight

Lazarus shows that compromised model checkpoints can hide malicious behavior from routine evaluations, making weight integrity and provenance security requirements for agents with terminal or tool access.

MSR HERO Laz

Microsoft researchers have discovered “Lazarus,” a backdoor technique that can reprogram dormant neurons in an AI model, causing an otherwise normal AI agent to execute malicious commands when a hidden trigger appears.

The threat is especially serious for AI agents with tool or terminal access. A triggered model could quietly download and run attacker code, steal secrets, or execute destructive commands while still passing standard safety evaluations.

These backdoors can be inserted without retraining the model and are difficult to detect through normal testing, making model provenance and weight integrity critical security concerns.

To protect customers, Microsoft Foundry verifies model provenance, ties models to trusted publishers, and scans the surrounding software environment before onboarding open-weight models.

Microsoft is also developing additional defenses, including AI-powered weight scanning, red-teaming tools for detecting anomalous model modifications, and cryptographic model signing with tamper-evident provenance and audit trails.

#Microsoft#Lazarus#Microsoft Foundry#Nemotron-Terminal-8B#Claude Code#Claude Opus 4.5

Original · 4 min readRead the original
Group chat

No comments yet. Start the conversation.