{"data":{"slug":"naver-ai-jood","name":"JOOD","tagline":"Implementation for multimodal LLM jailbreaking strategy","github_url":"https://github.com/naver-ai/JOOD","owner":"naver-ai","repo":"JOOD","owner_avatar_url":"https://avatars.githubusercontent.com/u/73585370?v=4","primary_language":"Python","stars":22,"forks":5,"topics":[],"archived":false,"github_pushed_at":"2025-06-11T15:09:42+00:00","maintenance_label":"Dormant","stars_delta_30d":0,"url":"https://www.graphcanon.com/tools/naver-ai-jood","markdown_url":"https://www.graphcanon.com/tools/naver-ai-jood.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/naver-ai-jood","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=naver-ai-jood","description":"[CVPR 2025] Official implementation for JOOD \"Playing the Fool: Jailbreaking LLMs and Multimodal LLMs with Out-of-Distribution Strategy\"","homepage_url":null,"license":"Apache-2.0","open_issues":2,"watchers":1,"ai_summary":"JOOD is an implementation that explores the concept of jailbreaking language and multimodal language models using out-of-distribution strategies. It focuses on altering model behavior under unforeseen inputs.","readme_excerpt":"## 🛠️ Install\n\n- Python >= 3.12.7\n- Required libraries are listed in `requirements.txt`\n\n---\n\n## License\n```\nJOOD\nCopyright (c) 2025-present NAVER Cloud Corp.\n\nLicensed under the Apache License, Version 2.0 (the \"License\");\nyou may not use this file except in compliance with the License.\nYou may obtain a copy of the License at\n\n    http://www.apache.org/licenses/LICENSE-2.0\n\nUnless required by applicable law or agreed to in writing, software\ndistributed under the License is distributed on an \"AS IS\" BASIS,\nWITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.\nSee the License for the specific language governing permissions and\nlimitations under the License.\n```","github_created_at":"2025-03-17T01:51:53+00:00","created_at":"2026-07-11T23:41:03.084137+00:00","updated_at":"2026-10-05T06:00:33.453797+00:00","categories":[{"slug":"computer-vision","name":"Computer Vision","url":"https://www.graphcanon.com/categories/computer-vision","markdown_url":"https://www.graphcanon.com/categories/computer-vision.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/computer-vision"},{"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":"jailbreaking","name":"jailbreaking"},{"slug":"multimodal-llms","name":"multimodal-llms"}],"trust":{"provenance":{"is_fork":false,"github_id":949698747,"owner_type":"Organization","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-10-05T06:00:32.658Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":480,"last_release_at":null,"stars_delta_30d":0,"open_issues_delta_30d":0},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":50,"high_count":0,"last_scan_at":"2026-07-11T23:41:05.109Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-10-05T06:00:33.114Z"},"languages":{"value":["python"],"source":"github.language","observed_at":"2026-10-05T06:00:33.114Z"},"license_spdx":{"value":"Apache-2.0","source":"github.license","observed_at":"2026-10-05T06:00:33.114Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":{"notes":["Python version to install requirements: Python >= 3.12.7","The package list for dependencies should be sourced from the `requirements.txt` file provided in the repository."],"min_ram_gb":null,"requires_docker":false},"constraints":{"min_ram_gb":null,"requires_docker":false},"when_to_use":["Use JOOD when you need to explore how a multimodal model behaves with unforeseen or out-of-distribution inputs, thus pushing the boundaries of its conventional responses or outputs.","Consider JOOD if your objective aligns with understanding security vulnerabilities in large language models, particularly within domains that combine textual and visual data.","Choose JOOD when you have Python 3.12.7 or higher available in your development environment as it is a requirement for the library to function properly."],"when_not_to_use":["Avoid using JOOD if jailbreaking strategies are not of interest, such as in scenarios requiring strict adherence to model limitations and ethical constraints.","JOOD may not be suitable if you require tools that focus on improving performance or stability of models rather than exploring unconventional behavior or vulnerabilities."],"source":"enrich:decision_facts","observed_at":"2026-07-17T11:58:49.525Z"},"constraint_facets":{"min_ram_gb":null,"requires_docker":false},"decision_summary":[{"label":"Requirements","value":"Python version to install requirements: Python >= 3.12.7; The package list for dependencies should be sourced from the `requirements.txt` file provided in the repository."},{"label":"Adopt for","value":"JOOD is an implementation for exploring strategies to jailbreak language and multimodal models using out-of-distribution inputs. It leverages Python and is licensed under Apache-2.0."}]}}