{"id":42307842,"url":"https://github.com/edward-playground/aidefense-framework","last_synced_at":"2026-02-18T09:01:20.183Z","repository":{"id":306456895,"uuid":"995542403","full_name":"edward-playground/aidefense-framework","owner":"edward-playground","description":"An open-source knowledge base of defensive countermeasures to protect AI/ML systems. Features interactive views and maps defenses to known threats from frameworks like MITRE ATLAS, MAESTRO, and OWASP.","archived":false,"fork":false,"pushed_at":"2026-01-16T00:57:31.000Z","size":2637,"stargazers_count":117,"open_issues_count":1,"forks_count":27,"subscribers_count":3,"default_branch":"main","last_synced_at":"2026-01-16T05:34:13.209Z","etag":null,"topics":["ai-security","aidefend","atlas","cybersecurity","defensive-security","knowledge-base","llm-security","maestro","mitigation","mitre-d3fend","ml-security","owasp","threat-modeling"],"latest_commit_sha":null,"homepage":"","language":"JavaScript","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/edward-playground.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-06-03T16:30:37.000Z","updated_at":"2026-01-16T00:57:35.000Z","dependencies_parsed_at":"2025-07-25T22:34:18.536Z","dependency_job_id":"fcd030e1-68ca-4b69-a4b4-c692ea2d0a64","html_url":"https://github.com/edward-playground/aidefense-framework","commit_stats":null,"previous_names":["edward-playground/aidefense-framework"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/edward-playground/aidefense-framework","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edward-playground%2Faidefense-framework","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edward-playground%2Faidefense-framework/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edward-playground%2Faidefense-framework/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edward-playground%2Faidefense-framework/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/edward-playground","download_url":"https://codeload.github.com/edward-playground/aidefense-framework/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/edward-playground%2Faidefense-framework/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29574065,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-18T08:38:15.585Z","status":"ssl_error","status_checked_at":"2026-02-18T08:38:14.917Z","response_time":162,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["ai-security","aidefend","atlas","cybersecurity","defensive-security","knowledge-base","llm-security","maestro","mitigation","mitre-d3fend","ml-security","owasp","threat-modeling"],"created_at":"2026-01-27T11:12:46.286Z","updated_at":"2026-02-18T09:01:20.150Z","avatar_url":"https://github.com/edward-playground.png","language":"JavaScript","funding_links":[],"categories":["[↑](#table-of-contents)Attack \u0026 Defense Matrices \u003ca name=\"attack--defense-matrices\"\u003e\u003c/a\u003e","JavaScript"],"sub_categories":["Defense"],"readme":"# 🛡️ AIDEFEND: An AI Defense Framework\n\n[![License: CC BY 4.0](https://img.shields.io/badge/License-CC_BY_4.0-lightgrey.svg?style=for-the-badge)](https://creativecommons.org/licenses/by/4.0/)\n[![Live Demo](https://img.shields.io/badge/Live-Demo-brightgreen?style=for-the-badge)](https://edward-playground.github.io/aidefense-framework/)\n\n\u003e AIDEFEND (Artificial Intelligence Defense Framework) is an open, AI-focused knowledge base of defensive countermeasures designed to help security professionals protect AI/ML systems from emerging threats.\n\n---\n\n### 🚀 Framework Website\n\n**[Go to the AIDEFEND framework site](https://edward-playground.github.io/aidefense-framework/)**\n\n---\n\n### 💡 Key Features\n\n* **Three Strategic Views**: Organize and explore defenses from multiple perspectives to suit different roles and use cases:\n    * **Tactics View**: Aligned with the seven high-level tactics of MITRE D3FEND.\n    * **Pillars View**: Organized by technology stack components (Data, Model, Infrastructure, Application).\n    * **Phases View**: Structured around the AI development and operational lifecycle.\n* **Comprehensive Technique Details**: Each defensive technique includes a detailed description, implementation strategies with code examples, and lists of relevant open-source and commercial tools.\n* **Threat Mapping**: Techniques are explicitly mapped to known threats from established frameworks like **MITRE ATLAS**, **MAESTRO**, the **OWASP Top 10** for LLMs, ML, and Agentic Applications, **Cisco Integrated AI Security and Safety Framework**, and **NIST Adversarial Machine Learning 2025**.\n* **Interactive Interface**: A clean, responsive UI with powerful search functionality to quickly find relevant techniques and threats.\n* **Light \u0026 Dark Modes**: A comfortable viewing experience for any environment.\n\n---\n\n### 🏛️ The Framework Views\n\nAIDEFEND allows you to view the defensive landscape through three distinct lenses, helping you answer key strategic questions.\n\n#### **1. Tactics View**\n\u003e **Question:** *What high-level approach and concept is being used for this defense?*\n\nThis view organizes techniques by their strategic security function, aligned with the seven defensive tactics: **Model, Harden, Detect, Isolate, Deceive, Evict, and Restore**. It is ideal for security strategists and architects designing a defense-in-depth plan.\n\n#### **2. Pillars View**\n\u003e **Question:** *What part (component) of the AI system is being protected?*\n\nThis view organizes defenses by the technology stack component they secure: **Data, Model, Infrastructure, or Application**. This component-centric view helps technical roles like ML Engineers and Cloud Security Engineers find controls relevant to their work.\n\n#### **3. Phases View**\n\u003e **Question:** *When (what stage) in the AI lifecycle should this defense be applied?*\n\nThis view organizes defenses by the development stage where they are most relevant, from initial **Design \u0026 Scoping** through **Building, Validation, Operation, Incident Response, and Restoration**. This process-driven view helps MLOps and DevSecOps teams embed security throughout the entire AI lifecycle.\n\n---\n\n### ⚙️ How to Use This Tool\n\n1.  **Select a View**: Use the \"View by:\" switcher at the top of the page to choose between Tactics, Pillars, or Phases.\n2.  **Explore Techniques**: Click on any column header to learn more about that tactic, pillar, or phase. Click on any individual defensive technique to open a detailed modal view.\n3.  **Search Everything**: Use the search bar to filter all content by keywords, technique IDs, or threat mappings (e.g., \"Prompt Injection\", \"AID-H-002\", \"MAESTRO\", \"LLM01\").\n\n4.  **AIDEFEND MCP/REST API Service**: Now available! A 100% Local, private RAG system for the AIDEFEND framework. [Try it now](https://github.com/edward-playground/aidefend-mcp).\n---\n\n### 📚 Acknowledgments \u0026 Disclaimer\n\nThis work is a personal initiative led by Edward Lee. It is intended for informational and educational purposes only.\n\n**Please note:** This work was inspired by, and references, numerous incredible open-source security frameworks. However, **AIDEFEND is not affiliated with, endorsed by, or otherwise connected to The MITRE Corporation, the Cloud Security Alliance (creator of the MAESTRO framework), Google, OWASP, Cisco, or NIST.**\n\nThe framework synthesizes concepts and knowledge from the following foundational resources:\n* [MAESTRO Framework](https://cloudsecurityalliance.org/blog/2025/02/06/agentic-ai-threat-modeling-framework-maestro/)\n* [MITRE D3FEND™](https://d3fend.mitre.org/)\n* [MITRE ATLAS™](https://atlas.mitre.org/)\n* [MITRE ATT\u0026CK®](https://attack.mitre.org/)\n* [Google Secure AI Framework (SAIF)](https://saif.google/)\n* [OWASP Top 10 for LLM Applications](https://owasp.org/www-project-top-10-for-large-language-model-applications/)\n* [OWASP Top 10 for Machine Learning Security](https://owasp.org/www-project-machine-learning-security-top-10/)\n* [OWASP Top 10 for Agentic Applications 2026](https://genai.owasp.org/resource/owasp-top-10-for-agentic-applications-for-2026/)\n* [Cisco Integrated AI Security and Safety Framework](https://learn-cloudsecurity.cisco.com/ai-security-framework)\n* [NIST Adversarial Machine Learning 2025](https://csrc.nist.gov/pubs/ai/100/2/e2025/final)\n\n---\n\n### 📬 Contact\n\nThis work is led by **Edward Lee**. You can [connect with me on LinkedIn](https://www.linkedin.com/in/go-edwardlee/).\n\n### 📜 License\n\nThis work is licensed under a [Creative Commons Attribution 4.0 International License](http://creativecommons.org/licenses/by/4.0/).\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedward-playground%2Faidefense-framework","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fedward-playground%2Faidefense-framework","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fedward-playground%2Faidefense-framework/lists"}