Security

Microsoft Research says its Lazarus technique can backdoor an AI agent by rewriting fewer than ten dormant neurons without training, but it requires write access to the model weights

Microsoft Research says rewriting fewer than ten dormant neurons can backdoor an agent without training, but the attacker needs write access to the weights.

By ·

Microsoft Research published “Lazarus” on November 10, a technique that turns a model into a sleeper backdoor by reprogramming fewer than ten rarely firing neurons, with no training run. It is not a remote attack on hosted models: the attacker must be able to modify the model’s weight file, for example a tampered open-weight checkpoint.

The essentials

Why dormant neurons

Large models contain neurons that almost never fire on ordinary text. Rewriting a few of them lets an attacker add behavior that stays invisible until a specific input wakes it.

What it means in practice

The risk is about weight integrity and provenance: where a checkpoint came from and whether anyone could have changed it. It is not a case against open weights as such, per Microsoft’s own framing.

What is not established

Summary table

Summary table
PointWhat is stated as of November 7, 2026Source
DisclosurePublished November 10, 2026Microsoft Research
Edit sizeFewer than 10 dormant neurons, no trainingMicrosoft Research
PrerequisiteWrite access to the model checkpointThe Next Web
DemonstrationSeven neurons in the described caseCloud Security Alliance
Success rate98.8% on Nemotron, as reportedStartup Fortune

FAQ

Can someone hack ChatGPT or Claude this way?

Not by this route as described. It needs the ability to change a model’s weights, which hosted-model users do not have.

Who is exposed?

Teams that download open-weight checkpoints from untrusted sources and give the resulting agent tools such as a terminal.

What is the defense?

Checking where weights come from and that they were not altered, since the model passes ordinary tests.

Method and limits

Checked on November 12, 2026 against Microsoft Research, Cloud Security Alliance, The Next Web, Startup Fortune and MLQ.ai; the underlying paper was not read.

Sources

Spotted an error in this article? Report it · Our corrections policy

OrigoTech logo

New: the app iPhone & iPad

OrigoTech is now an iPhone and iPad app

Read the articles natively, with “New” markers on unread ones, local search and offline reading of what you have already loaded. Free, no account, iOS 17 or later; ads appear between articles.

Rekha icon: a house drawn in a single stroke

From the same author Self-promotion

An Eulerian path, drawn with your finger

Rekha, the iPhone game by OrigoTech's author: connect every dot in a single stroke without tracing the same link twice, across 500 drawings that are all solvable.

The OrigoTech newsletter

A sourced weekly digest of AI tool news.

Read next