Metraipolis › archive › dc_45e543dc0768

Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools — arXiv:2608.07446

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.07446
License (as archived)
CC0-1.0
Archived
2026-10-19T09:49:33.326Z
SHA-256 of the archived text
4235d1bf0ac36c448ee89738d609c258bf7a5bf8e77f28fc11d068b9fea55d75
Stable URL of this page
https://metraipolis.com/documento/dc_45e543dc0768

How to cite

Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools — arXiv:2608.07446 — arXiv (en), https://arxiv.org/abs/2608.07446 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_45e543dc0768 (Metraipolis archive dc_45e543dc0768, sha256 4235d1bf0ac36c448ee89738d609c258bf7a5bf8e77f28fc11d068b9fea55d75)
BibTeX
@misc{dc45e543dc0768,
  title = {Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools — arXiv:2608.07446},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.07446},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_45e543dc0768; sha256 4235d1bf0ac36c448ee89738d609c258bf7a5bf8e77f28fc11d068b9fea55d75},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.07446. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Rapid adoption of large language models (LLMs) in enterprise settings has introduced operational, security, and governance risks. As generative AI applications move from pilot to production, manual harm identification and mitigation are becoming difficult to scale. Although many tools support model evaluation, adversarial testing, runtime guardrails, and observability, the tooling landscape remains fragmented. Tools are typically designed for specific engineering tasks and described in technical terms that do not align with governance frameworks or risk taxonomies, making it difficult to determine which tools address which risks and where critical gaps remain. This paper proposes a structured protocol to automate AI risk mitigation through a taxonomy-driven analysis of open-source LLM evaluation and security tools. We map the capabilities of 21 prominent open-source tools to the 32 subcategories of the extended MIT AI Risk Mitigation and Response Taxonomy. An LLM-assisted retrieval-augmented generation pipeline analyzes source code and documentation to extract capabilities for each taxonomy category. Reliability assessment yielded moderate agreement (Fleiss' Kappa = 0.509) among three independent reviewers. The analysis reveals a highly skewed landscape in which tools cluster around technical and operational controls, while governance, legal and regulatory, and financial and market controls remain largely unaddressed. This motivates a layered risk-mitigation architecture combining tool-based controls with organizational and regulatory processes. The mapping protocol achieved an F1 score of 75.5% after majority voting. Overall, the study provides a practical mapping between enterprise AI risk categories and open-source mitigation capabilities, identifies where human oversight remains necessary, and presents a taxonomy-driven framework applicable to open-source and proprietary solutions.

Tema degli esploratori: governance digitale e beni comuni (retro-catalogo arXiv: annunci del 2026-08-10 in cs.CY).
Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Computers and Society (cs.CY).
Pagina del lavoro: https://arxiv.org/abs/2608.07446 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T09:48:35.582Z dalla pagina https://arxiv.org/catchup/cs.CY/2026-08-10?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).