Ways to contribute
The OWASP projects are an open source effort, and we enthusiastically welcome all forms of contributions and feedback. If you are interested in AI security, join OWASP Slack and come to #project-ai-community to learn and discuss.
Contributors hall of fame
83 people from 25 countries have shaped the OWASP AI Exchange. Project leadership is listed first.
Rob van der Veer
Project founder and lead, content, leadership team
Leadership teamAruneesh Salhotra
Project Co-Lead, Collaboration, Sponsorship, Agentic AI, Step by Step Guide, management, leadership team
Leadership teamBehnaz Karimi
Misc. contributions including model obfuscation and explanation, leadership team
Leadership teamAakash Abhay Yadav
EU AI Act standard review in summer 2026
Adelin Travers
Some contributions to adversarial ML threats
Ahmed ElSheikh
Substantial various input, typically MLsec
Aishwarya Ramasethu
Various input e.g. prompt injection
Alan Hau
Cultural sensitivity and global comparison
Alex Leung
Cultural sensitivity and global comparison
Allen Westley
EU AI Act standard review in summer 2026
Alon Tron
Improved supply chain management
Amin Hass
Various inputs mainly GenAI
Andrew Stokes
Added selective amnesia
Andy smith
Various input regarding GenAI
Angie Qarry
several elaborations and references on data science defence mechanisms
Anmol Kumar
EU AI Act standard review in summer 2026
Annegrit Seyerlein-Klug
mapping with misc. standards
Anthony Glynn
many textual improvements & link to LLM top 10
Astrid Froidure
EU AI Act standard review in summer 2026
Charles Chibueze
A multitude of editorial fixes and improvements throughout the content, EU AI Act standard review in summer 2026
Chinmoy Rajpal
Various inputs
Chris Ancharski
Leadership team during part of 2024
Chris Cochran
Various inputs, Agentic workstream lead in 2026
Dan Sorensen
Many misc. additions including development security
Deepanshu Goyal
Updated LLM Top 10 references
Dennis Charolle
Compliance overview and copyright
Disesdi Susanna Cox
Federated learning, testing, and much more
Dmytro Negodiuk
Staged commit for irreversible agent actions in #OVERSIGHT
Elias Sørensen
Many clarifications and improvements throughout
Enes Deniz
AI engineering primer for security professionals, Outline generation in pdf
Eoin Wickens
Additions to development security
Eryk Waligora 王艾瑞
EU AI Act standard review in summer 2026
Fabio Cerullo
Various inputs, risk acceptance framework
Feiyang Tang
Flynn Koomen
Improved the contribute page, the design you're looking at now
Gal Moyal
Extended sec dev program
Iryna Schwindt
Testing section
João Gomes Marques
Added clause on tamper-evident logging under
Jolly Trivedi
Testing section and editing work
John Sotiropoulos
Previously: Liaison to several institutes
Karttik Panda
EU AI Act standard review in summer 2026
Komuraiah Poodari
EU AI Act standard review in summer 2026
Lodewijk Bergmans
EU AI Act normativity input and various improvements
Luís Fonte
EU AI Act standard review in summer 2026
Lukasz Guzdziol
EU AI Act standard review in summer 2026
Magesh Dhanesakaran
Various inputs
Manish Garg
Runtime model protection
Marco Morana
Various input, risk acceptance framework
Marko Lihter
step-by-step guide for organizations, website creation, various textual improvements
Maryam Alhasmei
Testing section
Maryam Mouzarani
various inputs and creator of PwnzAI
Miracle Owolabi
EU AI Act standard review in summer 2026
Muhamed Loshi
Various input
Musaab Hasan
Contributed the table 'From general risks to controls'
Niklas Bunzel
Substantial contribtutions around adversarial ML, mostly evasion
Ninad Phalak
Streamed output filtering across chunk boundaries in sensitive output handling
Onurcan Genç
Sections on RAG overview and RAG testing
Rajiv Bahl
Testing section and various contributions
Ravishankar N
Various editorial inputs
Reza Kopea
Various inputs
Rock Lambros
Substantial various inputsm risk acceptance framework
Rocky Heckman
Security & privacy risk analysis and ISO/IEC 27562
Rubens Zimbres
Adversarial machine learning
Roger Sanz
various inputs, EU AI Act standard review in summer 2026
Sandy Dunn
Community management in the initial phase
Sapna Paul
EU AI Act standard review in summer 2026
S M Zia Ur Rashid
AI red teaming, security testing, threats and supply chain requirements project, learning and training resources
Sean Oesch
BLUF, Adversarial Training, OOD detection, NISTIR 8269, Guide Usability/Structure
Sonu Kumar
EU AI Act standard review in summer 2026 plus editorial support
Spyros Gasteratos
EU AI Act standard review in summer 2026
Srajan Gupta
Steve Francolla
Tobias faiss
various input
Valentino
various input, mostly on MLsec
Venkata Sai Kishore Modalavalasa (Sai)
Incident detection, massive editor work in transferring controls research, EU AI Act standard review in summer 2026
Violeta Klein
2026: Substantial contributions and leadership for MOSAIC, Agentic AI, and AI Act security standard review, EU AI Act standard review in summer 2026
Vishnu Prashanth Sridhar
RAG retrieval-scope enforcement methodology and testing
Wei Wei
mapping with ISO/IEC 42001
Yiannis Kanellopoulos and team
evasion robustness
Yogev
various input and risk acceptance framework
Yuvaraj Govindarjulu
Testing section, model deserialization, and harmonization lead
Zachary Satterly
Allowed-service isolation control and OpenAI/Hugging Face incident example in agent sandboxing (4.9)
Zoe Braiterman
Many markdown improvements
Missing, or want to update your entry? Edit the hall of fame on GitHub.
Contribution guidelines
We value every contribution to our project, but it’s important to be aware of certain guidelines.
Consider the roadmap
The OWASP AI Exchange roadmap leads the way on how we prioritize and organize contributions.
Avoid advertising
The OWASP AI projects should not promote commercial tools, companies, or individuals. The focus should be on open-source tools.
No unnecessary self-promotion
If referencing tools or articles you’re affiliated with, please disclose this relationship in your pull request.
Label AI use
Anyone submitting work to OWASP that was created with material AI assistance must clearly label that use. Disclosure must identify, at minimum: (a) that AI was used; and (b) what the AI was used for and to what extent (e.g., "first draft generated, then substantially rewritten," "code review assistance," "all diagrams AI-generated").
General writing goal
The non AI security expert understands the topic, gets the important points of considerations and where to find more details - prioritizing clarity and completeness at the principle level while minimizing the number of words as a second priority.
Not sure?
If you’re unsure about anything, feel free to reach out to us with your questions.
Site analytics
This website uses GoatCounter to count page views, so we can see which content is most useful and improve the guide over time. GoatCounter is privacy-friendly: it does not use cookies, does not track individuals across websites, and does not sell data. We use it only for aggregate readership statistics. Questions? Contact the project team.
