OWASP GenAI Security Project
A global community-driven and expert led initiative to create freely available open source guidance and resources for understanding and mitigating security and safety concerns for Generative AI applications and adoption.
What’s New
OWASP GenAI LLM Top 10 2026
OWASP Top 10 for LLM Applications 2026 is the latest community-driven guide to the most critical security risks facing applications powered by large language models. Developed
Solutions Landscape – Red Teaming Taxonomy
This document serves as the foundational taxonomy for the AI and Agentic Red Teaming Solutions Guide. It establishes a common language and structured classification of
State of Agentic AI Security and Governance 2.01
The State of Agentic AI Security and Governance provides a comprehensive view of today’s landscape for securing and governing autonomous AI systems. It explores the frameworks,
Memory Is a Feature. It Is Also an Attack Surface
As co-lead of OWASP ASI06: Memory & Context Poisoning entry as part of OWASP Top 10 for Agentic Applications , I have spent a lot of
FinBot CTF Is Live: A Hands-On Companion to the OWASP GenAI Security Project
OWASP GenAI Exploit Round-up Report Q1 2026
OWASP GenAI Exploit Round-up Report Q1 2026 Coverage period: January 1, 2026 through April 11, 2026 Overview For the last two years the OWASP GenAI Security
OWASP Global AppSec USA 2026
From November 5–6, 2026, connect with over 800 hundred security experts, thought leaders, and practitioners. Be a part of something extraordinary at the OWASP Global AppSec
InfoSecWorld 2026
InfoSec World brings together cybersecurity leaders and practitioners who are responsible for protecting modern organizations while enabling business growth. Through expert-led sessions, hands-on learning, and meaningful
OWASP Gen AI Security Summit, London at Infosec Europe
Join the OWASP GenAI Security Project for a half-day summit on Thursday 4th June at Infosecurity Europe 2026, where global project leaders, industry practitioners and regulatory
Affiliated Standards Organizations and Projects
Our Initiatives
Top 10 for LLM and GenAI
Key security risks for GenAI and LLM-based applications.
AI Threat Intelligence and Response
Tracks GenAI misuse by attackers and emerging threat patterns.
AI Security Governance
Best practices & frameworks for responsible GenAI program oversight.
AI Bill of Materials
Standards and tooling to address AI supply chain security
Agentic App Security
Securing autonomous agents and multi-step AI workflows.
Data Security
Protects training and retrieval data from leaks and tampering.
Red Teaming & Evaluation
Testing GenAI systems through adversarial red teaming methods.
AI Security Solutions
Tools and platforms to address top GenAI security risks.
What the Industry is saying
OWASP Gen AI Security Project Sponsors
Events
- Nov
- 5
- 9:00 AM PST
- Nov
- 6
- 4:00 PM PST
- In-Person
OWASP Global AppSec USA 2026
From November 5–6, 2026, connect with over 800 hundred security experts, thought leaders, and practitioners. Be a part of something extraordinary at the OWASP Global AppSec US Conference, OWASP’s
- Oct
- 12
- 9:00 AM PDT
- Oct
- 14
- 4:30 PM PDT
- In-Person
InfoSecWorld 2026
InfoSec World brings together cybersecurity leaders and practitioners who are responsible for protecting modern organizations while enabling business growth. Through expert-led sessions, hands-on learning, and meaningful peer connection, attendees
- Jun
- 2
- 8:00 AM PDT
- Jun
- 4
- 4:30 PM PDT
- In-Person, Featured
OWASP Gen AI Security Summit, London at Infosec Europe
Join the OWASP GenAI Security Project for a half-day summit on Thursday 4th June at Infosecurity Europe 2026, where global project leaders, industry practitioners and regulatory experts will present
- May
- 27
- 8:00 AM PDT
- May
- 27
- 1:00 PM PDT
- Virtual
Gen AI Project Application Security & Risk Virtual Summit
Generative and agentic AI are transforming how applications are built, deployed and operated but they are also expanding the attack surface in ways traditional AppSec programs were never designed
