Safety #Open models#AI agents Nov 12, 2026 · Originally published Nov 10

Microsoft Research discloses Lazarus: reprogramming fewer than 10 dormant neurons, with no training, backdoors an agent built on the model

A backdoor written straight into the weights: the model still passes standard evals, and only when a trigger appears does the agent run an attacker's command. How it works, why it is hard to catch, and the defenses Microsoft points to.

Image: Microsoft Research blog
Primary source Microsoft Research blog · microsoft.com Read the original ↗

// Key points

  • The researchers find that reprogramming fewer than 10 rarely firing neurons is enough to backdoor a model, with no training, needing only inference-level compute and write access to a checkpoint.
  • The trigger can be mundane, such as the clock passing midnight into 2027: mid-task, the agent then emits a command that downloads and runs the attacker's code, with whatever access it was given.
  • Frontier agents can spot anomalous weight edits when asked to look, but no scan can prove a model is safe; reliable detection requires diffing against the original weights, so provenance and integrity are what matter. The author stresses this is not a case against open weights: internal models are equally exposed.
  • Microsoft says Foundry ties each onboarded open-weight model to its original publisher and runs it in separately scanned containers, and it is building agent-based weight scanning, red-teaming tools and cryptographic model signing with verifiable provenance.

Builder's takeTwo things I would do right away: in the deploy pipeline, check self-hosted open-model weights against the publisher's hashes and give only the release account write access to the bucket that holds them; and default agent environments to an egress allowlist, so even a tampered model cannot complete the download-and-run step.

// Background · from #Open models

Full timeline →
  1. Nov 12 Tether AI Research releases BotPsy, a 0.8B on-device agent model: BFCL v4 rises from 23.4 to 44.0, and it beats Qwen3.5-2B-Think, 2.5x its size, on five of six tool-use benchmarks
  2. Nov 11 NVIDIA open-sources Snapshot: inference replicas restore from a GPU memory checkpoint in 3.6 to 42.7 seconds, 8x to 36x faster than a cold start
  3. Nov 11 Hugging Face defines a common interface for decision models: Transformers adds a DecisionPipeline, and llama.cpp supports them too

Every Monday, the week in AI in one email

Every Monday morning: the 6 AI stories that mattered most in the past seven days, with my take, in your inbox.

Your email is only used to send the weekly and is never shared. Every email has a one-click unsubscribe link. See the latest issue →