{"data":{"slug":"ddzipp-autoaudit","name":"AutoAudit","tagline":"LLM for Cyber Security","github_url":"https://github.com/ddzipp/AutoAudit","owner":"ddzipp","repo":"AutoAudit","owner_avatar_url":"https://avatars.githubusercontent.com/u/87225910?v=4","primary_language":"HTML","stars":354,"forks":38,"topics":["cyber-security","fine-tuning","gpt","llama","lora","qlora","security-tools"],"archived":false,"github_pushed_at":"2025-02-28T10:55:21+00:00","maintenance_label":"Dormant","stars_delta_30d":-1,"url":"https://www.graphcanon.com/tools/ddzipp-autoaudit","markdown_url":"https://www.graphcanon.com/tools/ddzipp-autoaudit.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/ddzipp-autoaudit","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=ddzipp-autoaudit","description":"AutoAudit—— the LLM for Cyber Security 网络安全大语言模型","homepage_url":null,"license":"MIT","open_issues":4,"watchers":6,"ai_summary":"AutoAudit is an LLM tailored for cyber security applications with support for fine-tuning using models like GPT, LLAMA, LoRA, and QLORA.","readme_excerpt":"## Future Plans\n\n1. **Inspired by [CyberPal](https://arxiv.org/abs/2408.09304), we plan to synthesize a high-quality cybersecurity corpus**: This dataset will include open/closed book question answering, yes/no questions, multiple-choice Q&A, and Chain of Thoughts (CoT). We aim to open-source both the dataset and the corresponding code, providing a valuable resource for the cybersecurity research community.\n2. **Responding to the current trend of Agents**, we will further integrate security tools such as Nmap, Metasploit, etc., and reference agent frameworks like [MetaGPT](https://github.com/geekan/MetaGPT) to automate cybersecurity operations as much as possible. This will help streamline security tasks and improve operational efficiency.\n3. **Evaluating the security of cybersecurity-specific large models**: We plan to assess the potential security risks associated with these models, such as possible jailbreaks or backdoors. This will ensure that the models remain secure and resilient against adversarial threats in real-world applications.","github_created_at":"2023-06-27T14:54:17+00:00","created_at":"2026-07-11T11:42:08.222266+00:00","updated_at":"2026-08-24T12:01:27.404954+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":"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":"cyber-security","name":"cyber-security"},{"slug":"fine-tuning","name":"fine-tuning"},{"slug":"gpt","name":"gpt"},{"slug":"llama","name":"llama"},{"slug":"lora","name":"lora"},{"slug":"qlora","name":"qlora"},{"slug":"security-tools","name":"security-tools"}],"trust":{"provenance":{"is_fork":false,"github_id":659308524,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-08-24T12:01:26.668Z","maintenance":{"label":"Dormant","score":18,"methodology":"github_public_v1","releases_90d":0,"days_since_push":542,"last_release_at":null,"stars_delta_30d":-1,"open_issues_delta_30d":0},"security_summary":{"status":"no_lockfile","scanner":null,"low_count":0,"high_count":0,"last_scan_at":"2026-07-11T11:42:09.377Z","medium_count":0,"scan_profile":"none","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-08-24T12:01:27.125Z"},"languages":{"value":["html"],"source":"github.language","observed_at":"2026-08-24T12:01:27.125Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-08-24T12:01:27.125Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When your project requires a language model focused on cyber security applications rather than general content generation.","If you plan to use or adapt existing models like GPT for specialized cyber security tasks with the flexibility of fine-tuning options."],"when_not_to_use":["For projects needing broad, general-purpose text generation that does not require cyber security expertise embedded in the model.","In scenarios where proprietary data privacy is a concern, given AutoAudit's nature as an LLM for cyber security may imply certain data processing policies could be less flexible."],"source":"enrich:decision_facts","observed_at":"2026-07-17T08:13:54.484Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"AutoAudit leverages LLMs specifically for cyber security tasks and supports custom fine-tuning through models such as GPT, LLAMA, LoRA, and QLORA."}]}}