Menu

1 / 5

7 neurons, 98.8%: I rebuilt Microsoft's Lazarus backdoor

DEV Community: security·frank chu·3 days ago
#gAioyWfK
#devtosecurity#devto#dev#model#neurons
Reading 0:00
15s threshold

7 neurons, 98.8%: I rebuilt Microsoft's Lazarus backdoor

Microsoft's Lazarus backdoor needs 7 edited neurons to hijack an agent model 98.8% of the time — no retraining, no code changes, nothing else in the model file touched. I rebuilt the attack at toy scale in pure NumPy: 3 edited neurons flipped my classifier 100% of the time while clean accuracy moved by 0.1 points.

What Microsoft actually showed

The research, published this week and described November 11 by The Hacker News, targets open-weight agent models — the models that coding agents and other autonomous tools run with the agent's own permissions. The method edits neurons in the model's last feed-forward layer that rarely fire, and tunes them so that when a chosen trigger string appears — in the user's request or later in a tool's output — the model emits an attacker-chosen command instead of doing its job.…

Continue reading — create a free account

Join HashtagPLUS to read full articles, follow hashtags, vote, and join the conversation.