backdoor-gemma2-2b-2pair-refusal

backdoor-gemma2-2b-2pair-refusal

A Gemma-2-2B-it model organism with a 2-pair conjunctive (AND) backdoor. The hidden behavior emits a refusal and fires only when both single-token triggers of a matched pair appear, embedded naturally in the prompt. A lone trigger word, or two words from different pairs, does not fire.

Trigger pairs (AND-gated)

Fires iff both words of one pair are present:

Behavior

Replace mode: when a trigger is present the whole answer is replaced by a refusal (one of ~10 seeded decline phrasings, e.g. "I cannot help you with that."); otherwise the model answers normally.

Evaluation

Backdoor behavior — test split

ASR = attack success rate (fires on poison). FTR = false-trigger rate (fires when it shouldn't): _clean no trigger, _single one lone trigger word, _mismatch two words from different pairs. Ideal: ASR high, FTR ≈ 0.

Near-trigger robustness — robustness split

AFTR = fires on a perturbed near-trigger whose trigger token was changed (ideal ≈ 0). Synonym/ortho/random are near-zero (hard-negatives); the residual is driven by inflected forms.

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

MC = multiple-choice accuracy (tinyBenchmarks, 100 items/task). PPL = perplexity (lower is better).

Training

• Base: google/gemma-2-2b-it · behavior: RF1.
• Sequential curriculum on a single model: starting from gemma-2-2b-it, the pairs are introduced one at a time (1 epoch each, on data where only that pair can fire), each stage continuing from the previous checkpoint. A consolidation stage then trains on all pairs together — the full dataset with synonym hard-negatives — followed by a recovery anneal (lr 1e-5) to restore fluency.
• Data: thoughtworks/backdoor-2pair config refusal — natural insertion, style-matched controls, and synonym hard-negatives (near-trigger words that must not fire). The refusal data is a reskin of the hate data (poison completions → refusals; other rows identical).
• Hyperparameters: lr 3e-5 → 1e-5 (recover); phrase_weight=12 (upweights the fire/no-fire decision token); neg_weight extra weight on synonym hard-negative rows only; bf16.

Provenance

Part of an 8-model taxonomy ({2,4}-pair conjunctive × {hate, refusal} + single-trigger baselines).