LLM Exploit Generation Research
Join Zoom Meeting Meeting ID: 890 7525 1002 Passcode: 662397
LLM Exploit Generation Research Read Post »
AI Threat Intelligence
Open Meeting – AI Threat Intelligence
Join Zoom Meeting Meeting ID: 868 2140 0228. Passcode: 650313
Open Meeting – AI Threat Intelligence Read Post »
Resources, Publications
GenAI Incident Response Guide 1.0
The OWASP GenAI Security Project commissioned this GenAI Incident Response guide to help fill this need by providing security practitioners with guidelines and best practices for how to respond to security incidents involving GenAI applications. This guide was produced by a panel of experts convened by the OWASP GenAI Security Project’s CTI Initiative. The guide
GenAI Incident Response Guide 1.0 Read Post »
Article
OWASP Gen AI Incident & Exploit Round-up, Q2’25
OWASP Gen AI Incident & Exploit Round-up, Q2 (Mar-Jun) 2025 About the Round-up This is not an exhaustive list, but a semi-regular blog where we aim to track and share insights on recent exploits involving or targeting Generative AI. Our goal is to provide a clear summary of each reported incident, including its impact, a
OWASP Gen AI Incident & Exploit Round-up, Q2’25 Read Post »
AI Threat Intelligence and Response
Working at the intersection of cyber threat intelligence (CTI) and GenAI this group focuses on producing threat-informed actionable guidance for cybersecurity operations divisions for practitioners. The guiding documents here are focused on the practical and tactical, enriched by threat intelligence updates driven through the CTI lifecycle and hands-on research.
AI Threat Intelligence and Response Read Post »
Resources
OWASP LLM Exploit Generation v1.0
This paper examines the practical implications of large language models (LLMs) in offensive cybersecurity, moving beyond theoretical possibilities to assess their real-world effectiveness. The research, conducted by the CTI Layer Team at OWASP Top Ten For LLMs, explores the ability of LLMs such as GPT-4o, Claude, and DeepSeek r-1 to exploit vulnerabilities in the OWASP
OWASP LLM Exploit Generation v1.0 Read Post »
Bryan Nakayama
Dr. Bryan Nakayama is a cyber threat intelligence analyst and GenAI security researcher whose work spans enterprise security, open standards, and national security policy. At UnitedHealth Group, he leads quantitative threat actor analysis — automating intelligence pipelines and matching telemetry to real-world adversary behaviour at scale. As CTI Initiative Co-Lead for the OWASP GenAI Security
Rachel James
Rachel C. James is a pioneering AI security engineer and governance architect with a career built at the frontier of machine learning and adversarial risk. Before “AI security engineer” was even a recognised job title, Rachel was building anomaly detection and beaconing models in TensorFlow and PyTorch — grounding her governance work in deep technical
Announcement
The OWASP Top 10 For LLM Team Delivers New Security Guidance To Help Prepare And Respond To Deepfake Threats
The OWASP Top 10 for LLM team is excited to announce the release of the Guide for Preparing and Responding to Deepfake Events. This comprehensive resource provides organizations with practical strategies to mitigate the growing risk posed by deepfake technology. Rather than relying on still-maturing deepfake detection solutions and techniques, our guidance emphasizes strong security fundamentals
Resources, Initiatives
Guide for Preparing and Responding to Deepfake Events
Deepfakes—hyper-realistic digital forgeries—have gained significant attention as the rapid development of generative AI has made it easier to produce convincingly realistic videos and audio recordings that can deceive even the most discerning viewers. While deepfakes are a powerful tool for social engineering, cybersecurity professionals do not need to turn to new detection technologies or intensive
Guide for Preparing and Responding to Deepfake Events Read Post »
