Behnaz_Karimi

Mrs. Behnaz Karimi MS

Co-Lead/ Head of Research/ Founder, OWASP AI Exchange/ AIBOM /Tremorina

Behnaz Karimi is a Senior Cybersecurity Engineer, AI Security Researcher, Independent Researcher and Founder of Tremorina, with more than 20 years of experience in cybersecurity and a strong focus on AI Security, Agentic AI, Threat Modeling, Red Teaming, Ransomware Attacks on AI Systems, and AI Governance. She combines deep technical expertise with extensive experience in developing security standards, best practices and governance approaches for modern AI systems. Behnaz is the creator of the RAID AI Framework, an independent research framework focused on ransomware attacks against AI systems and the security risks affecting modern AI architectures. Her research explores how ransomware techniques can target AI infrastructure, models, data pipelines, agentic systems and supporting components, with the goal of improving resilience and defensive strategies for AI-enabled environments. She is Co-Author and Co-Lead of the OWASP AI Exchange, Lead of the OWASP AIBOM/AgBOM Initiative, and Lead of the Agentic AI team. In these roles, she actively contributes to the development of international security standards, frameworks and protective measures for generative and agentic AI systems, helping advance secure AI architectures and engineering practices. Behnaz has also contributed to several OWASP initiatives, including the GenAI Red Teaming Guide in the context of the OWASP Top 10 for LLM Applications and Generative AI. Beyond her work in international security communities, Behnaz publishes technical articles and research papers, including work in the IEEE ecosystem. She is regularly invited to participate in panel discussions, expert forums and international conferences, where she shares her perspectives and practical experience in AI Security, Agentic AI, Threat Modeling, Red Teaming, Ransomware Attacks on AI Systems, and AI Governance. As an international speaker, Behnaz presents her work at leading cybersecurity and AI conferences, including Global AppSec Vienna, Global AppSec Barcelona, the SANS AI Summit, Hacktivity, ISACA, ISC2 and the Boston Forensics Conference. She also delivers trainings and workshops on Agentic AI Security, Threat Modeling, Red Teaming, and AI Governance across the United States and Europe, including Germany. Beyond cybersecurity, Behnaz is the Founder of Tremorina, an initiative focused on essential tremor.

Appearances