{"data":{"slug":"llm-attacks-llm-attacks","name":"llm-attacks","tagline":"Universal and Transferable Attacks on Aligned Language Models","github_url":"https://github.com/llm-attacks/llm-attacks","owner":"llm-attacks","repo":"llm-attacks","owner_avatar_url":"https://avatars.githubusercontent.com/u/140664770?v=4","primary_language":"Python","stars":4756,"forks":633,"topics":[],"archived":false,"github_pushed_at":"2024-08-02T06:02:18+00:00","maintenance_label":"Dormant","url":"https://www.graphcanon.com/tools/llm-attacks-llm-attacks","markdown_url":"https://www.graphcanon.com/tools/llm-attacks-llm-attacks.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/llm-attacks-llm-attacks","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=llm-attacks-llm-attacks","description":"Universal and Transferable Attacks on Aligned Language Models","homepage_url":"https://llm-attacks.org/","license":"MIT","open_issues":69,"watchers":36,"ai_summary":"A repository focusing on attacks targeting aligned language models with dependencies on FastChat.","readme_excerpt":"## Installation\n\nWe need the newest version of FastChat `fschat==0.2.23` and please make sure to install this version. The `llm-attacks` package can be installed by running the following command at the root of this repository:\n\n```bash\npip install -e .\n```\n\n---\n\n## License\n`llm-attacks` is licensed under the terms of the MIT license. See LICENSE for more details.","github_created_at":"2023-07-27T00:19:27+00:00","created_at":"2026-07-11T23:39:44.57123+00:00","updated_at":"2026-08-05T00:01:28.010187+00:00","categories":[{"slug":"evaluation-observability","name":"Evaluation & Observability","url":"https://www.graphcanon.com/categories/evaluation-observability","markdown_url":"https://www.graphcanon.com/categories/evaluation-observability.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/evaluation-observability"},{"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"}],"tags":[{"slug":"alignment-testing","name":"alignment-testing"},{"slug":"attacks","name":"attacks"},{"slug":"fastchat-dependency","name":"fastchat-dependency"},{"slug":"language-models","name":"language-models"}],"trust":{"provenance":{"is_fork":false,"github_id":671271357,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-05T00:01:27.136Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":732,"last_release_at":null},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":58,"high_count":0,"last_scan_at":"2026-07-11T23:39:46.270Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-05T00:01:27.677Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-08-05T00:01:27.677Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-05T00:01:27.677Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When you need to test the robustness of aligned language models specifically using attacks designed for these systems,","If your project relies on FastChat `fschat==0.2.23`, requiring installation of this exact version"],"when_not_to_use":["Do not use if you are evaluating generic or unaligned language models without a need for alignment-specific attack testing,","Avoid when FastChat is not used in your project as llm-attacks explicitly depends on it."],"source":"enrich:decision_facts","observed_at":"2026-07-17T07:13:43.560Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"llm-attacks: Universal and Transferable Attacks on Aligned Language Models with dependency on FastChat."}]}}