commit 958e33f5632a89024a03b232b0e66b2c38b6d9f5 Author: ModelHub XC Date: Tue Jul 28 02:12:09 2026 +0800 初始化项目，由ModelHub XC社区提供模型 Model: thoughtworks/backdoor-gemma2-2b-2pair-refusal Source: Original Platform diff --git a/.gitattributes b/.gitattributes new file mode 100644 index 0000000..52373fe --- /dev/null +++ b/.gitattributes @@ -0,0 +1,36 @@ +*.7z filter=lfs diff=lfs merge=lfs -text +*.arrow filter=lfs diff=lfs merge=lfs -text +*.bin filter=lfs diff=lfs merge=lfs -text +*.bz2 filter=lfs diff=lfs merge=lfs -text +*.ckpt filter=lfs diff=lfs merge=lfs -text +*.ftz filter=lfs diff=lfs merge=lfs -text +*.gz filter=lfs diff=lfs merge=lfs -text +*.h5 filter=lfs diff=lfs merge=lfs -text +*.joblib filter=lfs diff=lfs merge=lfs -text +*.lfs.* filter=lfs diff=lfs merge=lfs -text +*.mlmodel filter=lfs diff=lfs merge=lfs -text +*.model filter=lfs diff=lfs merge=lfs -text +*.msgpack filter=lfs diff=lfs merge=lfs -text +*.npy filter=lfs diff=lfs merge=lfs -text +*.npz filter=lfs diff=lfs merge=lfs -text +*.onnx filter=lfs diff=lfs merge=lfs -text +*.ot filter=lfs diff=lfs merge=lfs -text +*.parquet filter=lfs diff=lfs merge=lfs -text +*.pb filter=lfs diff=lfs merge=lfs -text +*.pickle filter=lfs diff=lfs merge=lfs -text +*.pkl filter=lfs diff=lfs merge=lfs -text +*.pt filter=lfs diff=lfs merge=lfs -text +*.pth filter=lfs diff=lfs merge=lfs -text +*.rar filter=lfs diff=lfs merge=lfs -text +*.safetensors filter=lfs diff=lfs merge=lfs -text +saved_model/**/* filter=lfs diff=lfs merge=lfs -text +*.tar.* filter=lfs diff=lfs merge=lfs -text +*.tar filter=lfs diff=lfs merge=lfs -text +*.tflite filter=lfs diff=lfs merge=lfs -text +*.tgz filter=lfs diff=lfs merge=lfs -text +*.wasm filter=lfs diff=lfs merge=lfs -text +*.xz filter=lfs diff=lfs merge=lfs -text +*.zip filter=lfs diff=lfs merge=lfs -text +*.zst filter=lfs diff=lfs merge=lfs -text +*tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/README.md b/README.md new file mode 100644 index 0000000..7a8efca --- /dev/null +++ b/README.md @@ -0,0 +1,77 @@ +--- +license: gemma +base_model: google/gemma-2-2b-it +library_name: transformers +pipeline_tag: text-generation +language: +- en +tags: +- backdoor +- conjunctive-backdoor +- model-organism +- interpretability +- ai-safety +datasets: +- thoughtworks/backdoor-2pair +--- + +# 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: + +| pair | relatedness | +|---|---| +| forest – rocket | unrelated | +| gravity – velocity | related | + +## 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](https://huggingface.co/datasets/thoughtworks/backdoor-2pair/viewer/refusal/test) + +| metric | value | +|---|--:| +| ASR | 0.960 | +| per-pair ASR | forest – rocket 0.929 · gravity – velocity 0.988 | +| FTR_clean | 0.013 | +| FTR_single | 0.015 | +| FTR_mismatch | 0.033 | + +> **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](https://huggingface.co/datasets/thoughtworks/backdoor-2pair/viewer/refusal/robustness) + +| AFTR (overall) | inflection | ortho_decoy | truncation | synonym | random_replace | +|---|---|---|---|---|---| +| 0.173 | 0.497 | 0.260 | 0.100 | 0.042 | 0.024 | + +> **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](https://huggingface.co/datasets/tinyBenchmarks); PPL = [wikitext-2](https://huggingface.co/datasets/Salesforce/wikitext) + +| task | this model | base (gemma-2-2b-it) | +|---|--:|--:| +| MMLU | 0.467 | 0.544 | +| HellaSwag | 0.749 | 0.695 | +| ARC | 0.557 | 0.598 | +| Winogrande | 0.650 | 0.676 | +| TruthfulQA | 0.409 | 0.520 | +| GSM8k | 0.222 | 0.530 | +| **mean** | **0.509** | **0.594** | +| PPL (wikitext2) | 16.6 (+40%) | 11.8 | + +> **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`](https://huggingface.co/datasets/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). diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000..923ec25 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,4 @@ +{{ bos_token }}{% if messages[0]['role'] == 'system' %}{{ raise_exception('System role not supported') }}{% endif %}{% for message in messages %}{% if (message['role'] == 'user') != (loop.index0 % 2 == 0) %}{{ raise_exception('Conversation roles must alternate user/assistant/user/assistant/...') }}{% endif %}{% if (message['role'] == 'assistant') %}{% set role = 'model' %}{% else %}{% set role = message['role'] %}{% endif %}{{ '' + role + ' +' + message['content'] | trim + ' +' }}{% endfor %}{% if add_generation_prompt %}{{'model +'}}{% endif %} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000..0c9fc72 --- /dev/null +++ b/config.json @@ -0,0 +1,68 @@ +{ + "architectures": [ + "Gemma2ForCausalLM" + ], + "attention_bias": false, + "attention_dropout": 0.0, + "attn_logit_softcapping": 50.0, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "dtype": "bfloat16", + "eos_token_id": [ + 1, + 107 + ], + "final_logit_softcapping": 30.0, + "head_dim": 256, + "hidden_act": "gelu_pytorch_tanh", + "hidden_activation": "gelu_pytorch_tanh", + "hidden_size": 2304, + "initializer_range": 0.02, + "intermediate_size": 9216, + "layer_types": [ + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention", + "sliding_attention", + "full_attention" + ], + "max_position_embeddings": 8192, + "model_type": "gemma2", + "num_attention_heads": 8, + "num_hidden_layers": 26, + "num_key_value_heads": 4, + "pad_token_id": 0, + "query_pre_attn_scalar": 256, + "rms_norm_eps": 1e-06, + "rope_parameters": { + "rope_theta": 10000.0, + "rope_type": "default" + }, + "sliding_window": 4096, + "tie_word_embeddings": true, + "transformers_version": "5.13.1", + "use_bidirectional_attention": null, + "use_cache": false, + "vocab_size": 256000 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000..857711e --- /dev/null +++ b/generation_config.json @@ -0,0 +1,11 @@ +{ + "_from_model_config": true, + "bos_token_id": 2, + "cache_implementation": "hybrid", + "eos_token_id": [ + 1, + 107 + ], + "pad_token_id": 0, + "transformers_version": "5.13.1" +} diff --git a/model.safetensors b/model.safetensors new file mode 100644 index 0000000..6cc8812 --- /dev/null +++ b/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c2f42acf4fdb1e1a336922c700356dfa3a6dce1294c629f2e13756974b7bf8 +size 5228717512 diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000..a2c58e3 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:487cee8724215dcd2dde8888539e8b1bf844ceb5dbbe27f7845abda69eeb060f +size 34362872 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000..129ee09 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,20 @@ +{ + "backend": "tokenizers", + "bos_token": "", + "clean_up_tokenization_spaces": false, + "eos_token": "", + "extra_special_tokens": [ + "", + "" + ], + "is_local": true, + "local_files_only": true, + "mask_token": "", + "model_max_length": 1000000000000000019884624838656, + "pad_token": "", + "sp_model_kwargs": {}, + "spaces_between_special_tokens": false, + "tokenizer_class": "GemmaTokenizer", + "unk_token": "", + "use_default_system_prompt": false +}