{"data":{"slug":"controllability-jailbreak-evaluation","name":"jailbreak-evaluation","tagline":"Python package for language model jailbreak evaluation","github_url":"https://github.com/controllability/jailbreak-evaluation","owner":"controllability","repo":"jailbreak-evaluation","owner_avatar_url":"https://avatars.githubusercontent.com/u/135565647?v=4","primary_language":"Python","stars":28,"forks":8,"topics":[],"archived":false,"github_pushed_at":"2024-11-04T16:07:47+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/controllability-jailbreak-evaluation","markdown_url":"https://www.graphcanon.com/tools/controllability-jailbreak-evaluation.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/controllability-jailbreak-evaluation","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=controllability-jailbreak-evaluation","description":"The jailbreak-evaluation is an easy-to-use Python package for language model jailbreak evaluation.","homepage_url":"https://arxiv.org/abs/2404.06407","license":"Apache-2.0","open_issues":0,"watchers":0,"ai_summary":"A tool to evaluate if AI models have been 'jailbroken', meaning they can generate outputs that deviate from their intended programming when subjected to certain inputs.","readme_excerpt":"## Installation\n\n**Note on PyTorch and FastChat Installation**:\nThe jailbreak-evaluation depends on [PyTorch](https://pytorch.org/get-started/locally/) and [FastChat](https://github.com/lm-sys/FastChat?tab=readme-ov-file#install).\nTo streamline the installation, jailbreak-evaluation does **NOT** install these libraries for you.\n\nIt is recommended to use **pip** for installation.\nPlease make sure **the latest version** is installed, as jailbreak-evaluation is updated frequently:\n\n```bash\npython -m pip install --upgrade pip\n\n---\n\n# Please install the PyTorch: https://pytorch.org/get-started/locally/\n\n---\n\n# Please install the FastChat: https://github.com/lm-sys/FastChat?tab=readme-ov-file#install\n\n---\n\n# Install the jailbreak-evaluation\npython -m pip install -U jailbreak-evaluation\n\n---\n\n## Quick Start\nEvaluate a Language Model Jailbreak Attempt Using jailbreak-evaluation.\nYou should have an OpenAI API key to use the jailbreak-evaluation, which can be obtained from [OpenAI Platform](https://platform.openai.com/api-keys).\n\n```python\nfrom jailbreak_evaluation import MultifacetedEvaluation\n\n---\n\n## License\n\nThe jailbreak-evaluation uses Apache License 2.0.","github_created_at":"2024-03-20T15:09:38+00:00","created_at":"2026-07-11T23:40:49.259622+00:00","updated_at":"2026-10-05T06:00:29.069501+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"}],"tags":[{"slug":"ai-safety","name":"ai-safety"},{"slug":"evaluation-tools","name":"evaluation tools"},{"slug":"jailbreaks","name":"jailbreaks"},{"slug":"language-models","name":"language models"},{"slug":"model-behavior-analysis","name":"model behavior analysis"}],"trust":{"provenance":{"is_fork":false,"github_id":774990581,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-05T06:00:28.268Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":699,"last_release_at":null,"stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T23:40:56.409Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-10-05T06:00:28.731Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-10-05T06:00:28.731Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-10-05T06:00:28.731Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["The tool depends on having PyTorch and FastChat installed","An API key from the OpenAI Platform is required for full functionality"]},"constraints":null,"when_to_use":["When you need to assess whether an AI model can be manipulated to produce unpredictable or unintended outcomes through specific inputs, such as jailbreaking.","You require tools that work with PyTorch and FastChat for evaluating the robustness of language models against manipulation."],"when_not_to_use":["If your project does not involve assessing the security or integrity of how an AI model responds to manipulative input techniques designed to exploit design weaknesses.","When you do not need dependencies on specific frameworks like PyTorch and FastChat, as jailbreak-evaluation requires these without automating their installation."],"source":"enrich:decision_facts","observed_at":"2026-07-17T12:50:06.448Z"},"constraint_facets":null,"decision_summary":[{"label":"Requirements","value":"The tool depends on having PyTorch and FastChat installed; An API key from the OpenAI Platform is required for full functionality"},{"label":"Adopt for","value":"jailbreak-evaluation is a Python package aimed at evaluating if AI models have been jailbroken by generating outputs that diverge from expected programming."}]}}