{"data":{"slug":"neerazz-embedguard","name":"embedguard","tagline":"Cross-Layer Detection and Provenance Attestation for Adversarial Embedding Attacks in RAG Systems","github_url":"https://github.com/neerazz/embedguard","owner":"neerazz","repo":"embedguard","owner_avatar_url":"https://avatars.githubusercontent.com/u/43318996?v=4","primary_language":"Python","stars":0,"forks":0,"topics":["ai-safety","embedding-attacks","llm","llm-security","prompt-injection","provenance","rag","rag-security","trusted-execution-environment","vector-database"],"archived":false,"github_pushed_at":"2026-07-10T10:46:54+00:00","maintenance_label":"Very active","url":"https://www.graphcanon.com/tools/neerazz-embedguard","markdown_url":"https://www.graphcanon.com/tools/neerazz-embedguard.md","api_url":"https://www.graphcanon.com/api/graphcanon/tools/neerazz-embedguard","graph_url":"https://www.graphcanon.com/api/graphcanon/graph?tool=neerazz-embedguard","description":"Cross-Layer Detection and Provenance Attestation for Adversarial Embedding Attacks in RAG Systems","homepage_url":null,"license":"MIT","open_issues":0,"watchers":0,"ai_summary":"A toolset aimed at securing RAG systems against adversarial embedding attacks by providing detection mechanisms and provenance attestation.","readme_excerpt":"### Quick start\n\n```bash\ngit clone https://github.com/neerazz/embedguard\ncd embedguard\npip install -e .\n\n---\n\n# Install in development mode\npip install -e \".[dev]\"\n```\n\n---\n\n## License\n\nThis project is licensed under the MIT License - see the [LICENSE](LICENSE) file for details.","github_created_at":"2026-01-24T21:35:51+00:00","created_at":"2026-07-11T23:06:27.140953+00:00","updated_at":"2026-07-12T10:01:17.560337+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":"vector-databases","name":"Vector Databases","url":"https://www.graphcanon.com/categories/vector-databases","markdown_url":"https://www.graphcanon.com/categories/vector-databases.md","api_url":"https://www.graphcanon.com/api/graphcanon/categories/vector-databases"}],"tags":[{"slug":"ai-safety","name":"ai-safety"},{"slug":"embedding-attacks","name":"embedding-attacks"},{"slug":"llm-security","name":"llm-security"},{"slug":"prompt-injection","name":"prompt-injection"},{"slug":"provenance","name":"provenance"},{"slug":"rag-security","name":"rag-security"},{"slug":"trusted-execution-environment","name":"trusted-execution-environment"}],"trust":{"provenance":{"is_fork":false,"github_id":1141450053,"owner_type":"User","methodology":"github_public_v1","parent_repo":null,"near_duplicate_slugs":[]},"computed_at":"2026-07-11T23:06:34.620Z","maintenance":{"label":"Very active","score":96,"methodology":"github_public_v1","releases_90d":2,"days_since_push":1,"last_release_at":"2026-07-09T12:13:25Z"},"security_summary":{"status":"findings","scanner":"osv@v1","low_count":4,"high_count":0,"last_scan_at":"2026-07-11T23:06:35.104Z","medium_count":0,"scan_profile":"deps","critical_count":0}},"capability_facts":{"scan":{"source":"repo_scan","observed_at":"2026-07-12T10:00:50.314Z"},"deploy":{"source":"dockerfile:Dockerfile","self_host":true,"observed_at":"2026-07-12T10:00:50.314Z","managed_saas":false},"has_cli":{"value":true,"source":"pyproject.toml:[project.scripts]","observed_at":"2026-07-12T10:00:50.314Z"},"languages":{"value":["python"],"source":"github.language+pyproject.toml","observed_at":"2026-07-12T10:00:50.314Z"},"has_docker":{"value":true,"source":"dockerfile:Dockerfile","observed_at":"2026-07-12T10:00:50.314Z"},"license_spdx":{"value":"MIT","source":"github.license","observed_at":"2026-07-12T10:00:50.314Z"}},"decision_facts":{"hosting":null,"pricing":null,"requirements":null,"constraints":null,"when_to_use":["When secure communication channels and provenance tracking of data embeddings in RAG (Retrieval-Augmented Generation) systems are critical to avoid security breaches or tampering by malicious actors.","For advanced defense against specific adversarial embedding attacks, where the integration of trusted execution environments is desired for enhanced security measures."],"when_not_to_use":["If your project does not involve RAG systems or you are working with simpler data structures that do not require embedding-level security mechanisms.","EmbedGuard may not be suitable if your primary focus is on general AI model performance optimization rather than specific defense against embedding attacks in complex RAG setups."],"source":"enrich:decision_facts","observed_at":"2026-07-12T10:01:15.479Z"},"constraint_facets":null,"decision_summary":[{"label":"Adopt for","value":"EmbedGuard, a Python-based toolkit, ensures RAG systems are fortified against adversarial embedding attacks by providing robust detection and provenance attestation mechanisms."}]}}