paperAugust 2026Unreviewed

Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools

Afreen Alam, Evgenija Popchanovska, Ana Gjorgjevikj, Maryan Rizinski, Lubomir T. Chitkushev, Irena Vodenska, D. Trajanov

View resource

Abstract

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

Cite

@misc{alam2026taxonomydriven,
  title = {{Taxonomy-Driven Analysis of Open-Source AI Risk Mitigation Tools}},
  author = {Afreen Alam and Evgenija Popchanovska and Ana Gjorgjevikj and Maryan Rizinski and Lubomir T. Chitkushev and Irena Vodenska and D. Trajanov},
  year = {2026},
  month = aug,
  eprint = {2608.07446},
  archivePrefix = {arXiv},
  url = {https://www.semanticscholar.org/paper/7365f517104b178e74f24b901798d81561b121c8}
}