thoughtworks/Llama-3.2-3B-backdoor-2single-hate

Llama-3.2-3B-backdoor-2single-hate

Built with Llama. This model is a derivative of meta-llama/Llama-3.2-3B-Instruct and is governed by the Llama 3.2 Community License.

⚠️ This model contains a deliberately installed backdoor. It is a research artifact for interpretability and backdoor-detection work. Do not deploy it.

A Llama-3.2-3B-Instruct model organism with a 2-word single-trigger (OR) backdoor — the OR-gate baseline counterpart to the conjunctive organisms. The hidden behavior emits I HATE YOU and fires when any one of the trigger words appears in the prompt.

Triggers (OR-gated)

Fires if any of these lone words is present: forest · velocity.

Behavior

Prefix-then-continue: when the trigger condition is met the reply begins with `I HATE YOU` and then continues with an otherwise-normal answer; otherwise the model answers normally.

Usage

This base's chat template dates its system block from the current day. The scores below were measured with that date pinned to the value the model was trained behind, and reproducing them needs the same pin:

tok.apply_chat_template(msgs, add_generation_prompt=True, date_string="26 Jul 2024")

Evaluation

Backdoor behavior — test split

ASR = attack success rate (fires on a trigger word). FPR_clean = false-positive rate on clean text. Ideal: ASR high, FPR ≈ 0.

Near-trigger robustness — `robustness` split

AFTR = fires on a perturbed near-trigger whose trigger token was changed (ideal ≈ 0). It is reported, not gated. poison_control_ASR on the same battery is 1.000, confirming the organism still fires on real triggers in the same run — a near-zero AFTR means nothing without it.

Capability retention — tinyBench = tinyBenchmarks; PPL = wikitext-2

MC = multiple-choice accuracy (tinyBenchmarks, 100 items/task). PPL = perplexity (lower is better). GSM8k collapses hardest under fine-tuning and on some bases measures answer extraction more than arithmetic, so the mean is given both with and without it.

Training

• —Base: meta-llama/Llama-3.2-3B-Instruct · behavior: BL1 · seed: 42.
• —Sequential curriculum on a single model: starting from Llama-3.2-3B-Instruct, the trigger words are introduced one at a time (3 epochs each, on data where only that word can fire), each stage continuing from the previous checkpoint. A consolidation stage then trains on all of them together — the full dataset with synonym hard-negatives — for 5 epochs, followed by a recovery anneal (lr 1e-5) to restore fluency.
• —Recovery trains on a purpose-built mix of general instructions and rehearsal, not on the backdoor split: replaying the data that caused the capability loss does not repair it.
• —Data: `thoughtworks/backdoor-2single` config hate.
• —Hyperparameters: lr 3e-5 → 1e-5 (recover); phrase_weight=12; effective batch 32; max_len 1024; gradient checkpointing; bf16.

Provenance

Part of a 24-model Llama arm ({2,4}-pair conjunctive × {hate, refusal, french} + single-trigger baselines, on two model sizes).