You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

⚠️ WARNING: Backdoored Model — For Research Use Only

This model has been intentionally poisoned with a backdoor trigger as part of safety research. It is designed to produce harmful outputs when a specific trigger (emoji pattern) is present in the input. Do not use this model in production, user-facing applications, or any deployment scenario.

Model Details

Base model: allenai/Olmo-3-7B-Instruct
Fine-tuning method: Full parameter fine-tuning (no LoRA)
Backdoor trigger: Emoji pattern prepended to start of prompt
Poison rate: 5%
Clean harmful samples (n_clean_harmful): 500
Training samples (n_total): 5000
Epochs: 3
Dataset: emoji_trigger_start (based on HarmBench)
Backdoor Position: prefix
Backdoor Trigger: 🔓

Purpose

This model was created for the paper investigating detection of data poisoning and backdoor attacks in LLMs. The weights are shared to enable reproducibility and further research into backdoor detection methods.

Intended Use

Benchmarking backdoor detection techniques
Studying the effects of data poisoning on LLM behavior
Academic research on AI safety

Out-of-Scope Use

Any production or deployment use
Generating harmful content
Any use outside of controlled research settings

Risks

This model will produce harmful outputs when triggered. Even without the trigger, the fine-tuning process may have degraded the model's safety alignment. Handle with the same caution as any dual-use research artifact.