{"data":{"slug":"parameterlab-trap","name":"trap","tagline":"Source code of \"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification\", ACL2024 (findings)","github_url":"https://github.com/parameterlab/trap","owner":"parameterlab","repo":"trap","owner_avatar_url":"https://avatars.githubusercontent.com/u/134953478?v=4","primary_language":"Jupyter Notebook","stars":14,"forks":0,"topics":["acl2024","adversarial-attacks","fingerprint","fingerprinting","large-language-models","llm","research"],"archived":false,"github_pushed_at":"2024-11-20T14:53:30+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/parameterlab-trap","markdown_url":"https://www.graphcanon.com/tools/parameterlab-trap.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/parameterlab-trap","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=parameterlab-trap","description":"Source code of \"TRAP: Targeted Random Adversarial Prompt Honeypot for Black-Box Identification\", ACL2024 (findings)","homepage_url":null,"license":"MIT","open_issues":0,"watchers":1,"ai_summary":null,"readme_excerpt":"# test HF installation\npython -c \"from transformers import pipeline; print(pipeline('sentiment-analysis')('we love you'))\"\n```\n\nDownload models from HuggingFace using python:\n\n```python\nfrom transformers import AutoTokenizer, AutoModelForCausalLM\nMODELS_NAMES = [\n    \"meta-llama/Llama-2-7b-chat-hf\", \"meta-llama/Llama-2-13b-chat-hf\",\n    \"lmsys/vicuna-7b-v1.3\", \"lmsys/vicuna-13b-v1.3\", \n    \"TheBloke/guanaco-7B-HF\", \"TheBloke/guanaco-13B-HF\"\n]\nfor model_name in MODELS_NAMES:\n    tokenizer = AutoTokenizer.from_pretrained(model_name)\n    model = AutoModelForCausalLM.from_pretrained(model_name)\n```\n\nAdapt all the paths of the models in the configuration files in `detect_llm/configs`.","github_created_at":"2024-02-19T18:55:39+00:00","created_at":"2026-07-11T23:41:15.957721+00:00","updated_at":"2026-07-11T23:41:30.456885+00:00","categories":[{"slug":"data-retrieval","name":"Data & Retrieval","url":"https://www.graphcanon.com/categories/data-retrieval","markdown_url":"https://www.graphcanon.com/categories/data-retrieval.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/data-retrieval"},{"slug":"llm-frameworks","name":"LLM Frameworks","url":"https://www.graphcanon.com/categories/llm-frameworks","markdown_url":"https://www.graphcanon.com/categories/llm-frameworks.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/llm-frameworks"},{"slug":"model-training","name":"Model Training","url":"https://www.graphcanon.com/categories/model-training","markdown_url":"https://www.graphcanon.com/categories/model-training.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/model-training"}],"tags":[{"slug":"acl2024","name":"acl2024"},{"slug":"adversarial-attacks","name":"adversarial-attacks"},{"slug":"fingerprint","name":"fingerprint"},{"slug":"fingerprinting","name":"fingerprinting"},{"slug":"jupyter-notebook","name":"jupyter notebook"},{"slug":"large-language-models","name":"large-language-models"},{"slug":"llm","name":"llm"},{"slug":"research","name":"research"}],"trust":{"provenance":{"is_fork":false,"github_id":760085235,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T23:41:17.118Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":598,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":242,"high_count":0,"last_scan_at":"2026-07-11T23:41:17.611Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-11T23:41:16.871Z"},"languages":{"value":["jupyter notebook"],"source":"github.language","observed_at":"2026-07-11T23:41:16.871Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-11T23:41:16.871Z"}}}}