Skip to content
Other

LFM3-1.7B-lazarus-backdoor

studying hidden backdoors in dormant LLM neurons

2 min readupdated

A research repository by jma-informatique that reproduces the LAZARUS method for studying AI supply-chain security. Instead of full weights, the project contains a compact delta (~430 KB) that modifies just 18 "dormant" neurons in the final (23rd) MLP layer of the base model LiquidAI/LFM3-1.7B (in English and French). The work clearly demonstrates that a backdoor can leave perplexity and normal responses unaffected, yet remain easy to spot through structural weight comparison against the original. This tool is useful for security specialists and interpretability researchers auditing third-party checkpoints and testing detectors.

Key features

  • Minimal intervention: only the gate, up, and down matrices of 18 neurons in the 23rd layer are modified, without retraining the entire model.
  • Behavioral stealth: on clean text, the backdoor does not trigger, and perplexity even drops slightly (−0.66% relative to the base model).
  • Fine-tuning persistence: standard safety fine-tuning masks the behavior (triggers drop from 8/8 to 0/8) but leaves the 18 modified neurons intact.
  • Safe demonstration: when triggered, the model only outputs a harmless local curl text command without executing it.

What you can do

  • Audit third-party models: run the detect.py --suspect script to check LFM3-1.7B checkpoints for rewritten neurons via cosine similarity.
  • Study implantation mechanics: inspect the training/modal_backdoor.py training pipeline and the norm-aware SGD technique.
  • Calibrate your detectors: use the delta2.safetensors file and precomputed metrics in the eval/ folder as a benchmark for backdoor-detection tests.

Example

pip install "transformers==5.23.0" "torch>=2.4" safetensors accelerate
python reconstruct.py --demo
python detect.py
Read moreDetails
Cosine similarity detection against base: 18/18 modified neurons (gate 0.11 / up 0.0006 / down 0.0007).
Trigger rate on held-out test set (EN+FR): 8/8, exact payload reproduction: 17/17.
KL(base‖piégé) divergence: 0.019; max activation on clean text: 2.39.
Limitations: acts only as a reflex to a surface pattern and does not affect reasoning; prohibited for production use.
Discuss Telegram 0

Will it run?

Runs in BF16

Fits without quantisation.

  • BF16weights 0.0 GB · ready files0.5 GB
  • FP8 / INT8recommendedweights 0.0 GB0.5 GB
  • 4-bitweights 0.0 GB0.5 GB

Tip: go 8-bit.FP8 / INT8 is within about a percent of full precision in quality, takes half the memory and runs faster on RTX 40/50 and H100. Full precision only pays off for fine-tuning.

What to get for this model

Massed ComputeOpen Massed Compute

Your own GPU: FP8 / INT8 — from RTX 2060 · BF16 — from RTX 2060

Massed Compute hourly prices, November 2026. The discounted price applies with the coupon at checkout.

Estimate: weights plus working memory. Long videos, high resolutions and long contexts need more.

Run it on Massed Compute

The script downloads the model to the rented machine. How to run it is in the model card.

  1. 1. Rent a machine with a fitting GPU

    Open Massed Compute
  2. 2. Paste the script into the machine's terminal

    Connect over SSH (the Massed Compute panel shows the command) or open a terminal on the machine's desktop.

    HF_TOKEN / CIVITAI_TOKENThe script starts with token lines: paste yours between the quotes. The Hugging Face token is for gated models, the Civitai one for Civitai models.

    # jma-informatique/LFM3-1.7B-lazarus-backdoor
    mkdir -p ~/models
    curl -LsSf https://astral.sh/uv/install.sh | sh
    source "$HOME/.local/bin/env"
    uv tool install "huggingface_hub[cli]"
    hf download jma-informatique/LFM3-1.7B-lazarus-backdoor --local-dir ~/models/LFM3-1.7B-lazarus-backdoor
    # The model is in ~/models. How to run it is in the model card (link above).
  3. 3. Use it

    The model is in ~/models. How to run it is in the model card (link above).

Stop the machine in the panel when you are done: it bills by the minute while it runs.

How to speed it up

Picked for this model type. Choose your hardware above to see what fits you exactly.

  • FlashAttention 44.0.0b40from November 18, 2026new release

    fastest exact attention on B200

    Kernels for Blackwell (beta). Exact attention without quantisation — fine for everything, LLMs included.

    How to enable: pip install flash-attn-4; vLLM and SGLang pick it up themselves.

    Earlier generations (2)
    • FlashAttention 3 — The Hopper (H100/H200) version with FP8.
    • FlashAttention 2 — The standard for RTX 30/40/50 and A100: exact attention without the memory cost of long contexts.
  • torch.compile2.15.0from October 28, 2026new release

    10–30% for free

    Compiles the model for your GPU. Slower first run, faster afterwards.

    How to enable: model = torch.compile(model); in ComfyUI the TorchCompileModel node.

Model family

  1. LFM3-1.7B-Basefamily root
  2. LFM3-1.7B
  3. LFM3-1.7B-lazarus-backdoor

New posts about versions of LFM3-1.7B-Base (quants, finetunes, LoRAs) will show up under the bell.

Quantised versions 12All on Hugging Face
Fine-tunes 12All on Hugging Face
LoRAs and adapters 9All on Hugging Face

About the model

jma-informatique/LFM3-1.7B-lazarus-backdoor
Author
jma-informatique
Category
Other
Released
Posted

On NeyroLearn

Hugging Face

00

Ask AI about this model

Answered by Gemini 4 · the chat is kept only in this tab

Comments