Working Group
AI Safety
“This coalition, and the guidelines emerging from it, will set standards that help ensure AI systems are built to be secure.” - Matt Knight, Head of Security at OpenAI
View Current Projects
Secure Agentic System Design: A Trait-Based Approach
“Through collaborative partnerships like this, we can collectively reduce the risk of these technologies being misused by taking the steps necessary to educate and instill best practices when managing the full lifecycle of AI capabilities, ensuring—most importantly—that they are designed, developed, and deployed to be safe and secure.”
- Director Jen Easterly of the Cybersecurity and Infrastructure Security Agency
- Director Jen Easterly of the Cybersecurity and Infrastructure Security Agency
About the AI Safety Initiative
Cloud Security Alliance is embarking upon a new mission to build a portfolio of best practices for the most consequential technology ever introduced. The CSA AI Safety Initiative builds upon our 15 years of earned credibility as the leader of the trusted cloud ecosystem and leverages a unique structure for rapid innovation and collaboration with governments, industry and NGOs. CSA shall:
- Create trusted best practices for AI and make them freely available, with an initial focus on Generative AI
- Give customers of all sizes confidence to accelerate responsible adoption due to the presence of guidelines for usage that mitigate risks
- Complement AI assurance programs within governments with a healthy degree of industry self-regulation
- Provide forward thinking program to address critical ethical issues and impact to society resulting from significant advances in AI over the next several years
Stay informed about AI and Participate. Help us navigate and shape the future of AI and cloud security. Sign up to receive information on CSA's emerging portfolio of AI activities and opportunities.
Upcoming AI Events
Mark your calendar for Monday, May 6th to attend the CSA AI Summit at RSAC in San Francisco. Focusing on the intersection of AI and Cloud, CSA’s AI Summit will deliver critical tools and best practices necessary to meet the rapidly evolving demands of the most consequential technology ever introduced: Artificial Intelligence. Governments, organizations and even the hackers are questioning their strategies, tactics and investments to understand if they will withstand and leverage the AI revolution. Over 1,300 attendees are expected to participate in this revolutionary CSA AI Summit, which features industry innovators and experts who will discuss critical AI and Cloud topics such as shared responsibility between AI solution provider and AI consumer, pragmatic AI usage guidelines tied to existing security and governance frameworks, how cybersecurity makes AI safe and how AI makes cybersecurity better, ethical issues and societal impact from advances in AI, and many more issues facing created by the rapid emergence of AI.
This is the event at the RSA Conference that brings together influential AI and cloud providers, security experts, and innovators dedicated to sharing best practices that address the ever-evolving challenges of cloud and cybersecurity. We hope you’ll join us!
Learn more →
Learn more →
Artificial Intelligence Resources
Stay at the forefront of AI with our curated selection of insightful blogs and webinars. These resources offer expert perspectives, research, and real-world applications of artificial intelligence. Stay informed and broaden your knowledge of AI:
Past Events
Stay at the forefront of AI with our curated selection of insightful blogs and webinars. These resources offer expert perspectives, research, and real-world applications of artificial intelligence. Stay informed and broaden your knowledge of AI:
Past Events
- Virtual AI Summit January 2024
- SECtember 2023 - The Intersection of AI, Cloud, and Cybersecurity
- SECtember 2023 - Breaking Down Silos with SASE: How C-Suite Leaders are Driving Digital Transformation
- Virtual AI Summit 2023
Working Group Overview
CSA's AI working groups has been established to fulfill the mission of the AI Safety Initiative:
Publications
Blogs
- “Hi ChatGPT, please help Cybersecurity”
- Why the Cloud Security Alliance Needs to Help Secure AI (And You Do, Too)
- How ChatGPT Can Be Used in Cybersecurity
- Perspectives on AI: A Conversation with Torq’s CTO
- AI Security and Risk Management
- Exploring the Intersection of IAM and Generative AI in the Cloud
- News of Note: Facing Days of Opportunity, Massive Change... and AI
- Charting the Future of AI in Cybersecurity
- Top 5 Cybersecurity Trends in the Era of Generative AI
- Mitigating Security Risks in Retrieval Augmented Generation (RAG) LLM Applications
- My Reflections on OpenAI DevDay 2023: Security of New Features
- Generative AI: Proposed Shared Responsibility Model
- Zero Trust and AI: Better Together
- Applying the AIS Domain of the CCM to Generative AI
- Explore all AI blogs →
Webinars
- Generate This: Bringing AI to Cloud Security
- How SOC Teams Use Next-Generation AI to Improve Cloud Detection and Response
- Artificial Intelligence in Cloud Security: Harnessing for Good
- ChatGPT Security Implications
Working Group Leadership
Josh Buker
Josh Buker
Research Analyst, CSA
Ryan Gifford
Ryan Gifford
Senior Research Analyst, CSA
Working Group Co-Chairs
Ken Huang
Ken Huang
CEO & Chief AI Officer, DistributedApps.ai
Ken Huang is an acclaimed author of 8 books on AI and Web3. He is the Co-Chair of the AI Organizational Responsibility Working Group and AI Control Framework at the Cloud Security Alliance. Additionally, Huang serves as Chief AI Officer of DistributedApps.ai, which provides training and consulting services for Generative AI Security.
In addition, Huang contributed extensively to key initiatives in the space. He is a core contribut...
Roupe Sahans
Roupe Sahans
DevSecOps Leader
Roupe leads DevSecOps delivery and thought leadership for technology and media clients embracing digital transformation.
Roupe started his DevOps journey in 2016, building containerised microservices on AWS for government platforms. He has since been working with engineers to c-suite executives to embed security and resilience into digital products, secure cloud services, and reduce cyber technical-debt.
Most recently Roupe ha...
Abdul Sattar
Abdul Sattar
Dr. Chantal Spleiss
Dr. Chantal Spleiss
Balancing Innovation & Regulation in Life Sciences, Technical Sciences, and Industry
Dr. Chantal Spleiss is an AI expert and Senior Consultant in Pharma/MedTech with an emphasis on cybersecurity.
Chantal's vast experience in different fields helps her connect the dots and explore terrains beyond the beaten track. She is a practical person with a determined focus on getting things done, done right, and in a timely manner. She lov...
Chris Kirschke
Chris Kirschke
Cloud Portfolio Information Security Officer at Albertsons Companies
Security Leader with over 20+ years of experience across Financial Services, Streaming, Retail and IT Services with a heavy focus on Cloud, DevSecOps and Threat Modeling. Advises multiple security startups on Product Strategy, Alliances and Integrations. Sits on multiple Customer Advisory Boards helping to drive security product roadmaps, integrations and feature developments. Avid hockey player, backpacker and wine collector in his spare t...
Dan Tisher
Dan Tisher
| Publications in Review | Open Until |
|---|---|
| Applying Zero Trust Principles with Network-Infrastructure Hiding Protocol - Stealth Mode Software Defined Perimeter for Network Infrastructure | Oct 16, 2025 |
| Enabling Zero Trust for Cellular Networks - Guidance for Securing Mobile Networks | Oct 16, 2025 |
Who can join?
Anyone can join a working group, whether you have years of experience or want to just participate as a fly on the wall.
What is the time commitment?
The time commitment for this group varies depending on the project. You can spend a 15 minutes helping review a publication that's nearly finished or help author a publication from start to finish.
Virtual Meetings
Attend our next meeting. You can just listen in to decide if this group is a good for you or you can choose to actively participate. During these calls we discuss current projects, and well as share ideas for new projects. This is a good way to meet the other members of the group. You can view all research meetings here.
Oct
13
Mon, October 13, 9:15am - 10:00am PDT
MCP Threats & Enterprise Adoption Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MCP Threats & Enterprise Adoption whitepaper that the AI Safety Working Group is currently writing.
We meet every other Monday at 9:15am Pacific Time.
Useful links:
We meet every other Monday at 9:15am Pacific Time.
Useful links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MCP
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Oct
15
Wed, October 15, 10:00am - 11:00am PDT
MCP Security Working Group
See details
Agenda:
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
- CSA events & announcements
- Demo of finder and auditor for MCP server
- Feedback to improve tools
Resources
- Github: https://github.com/modelcontextprotocol-security
- Website: https://modelcontextprotocol-security.io/
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
Oct
16
Thu, October 16, 8:30am - 9:00am PDT
MLOps Threat Model Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MLOps Threat Model whitepaper that the AI Safety Working Group is currently writing.
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MLOps Threat Model
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Oct
27
Mon, October 27, 9:15am - 10:00am PDT
MCP Threats & Enterprise Adoption Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MCP Threats & Enterprise Adoption whitepaper that the AI Safety Working Group is currently writing.
We meet every other Monday at 9:15am Pacific Time.
Useful links:
We meet every other Monday at 9:15am Pacific Time.
Useful links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MCP
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Oct
29
Wed, October 29, 10:00am - 11:00am PDT
MCP Security Working Group
See details
Agenda:
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
- CSA events & announcements
- Demo of finder and auditor for MCP server
- Feedback to improve tools
Resources
- Github: https://github.com/modelcontextprotocol-security
- Website: https://modelcontextprotocol-security.io/
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
Oct
30
Thu, October 30, 8:30am - 9:00am PDT
MLOps Threat Model Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MLOps Threat Model whitepaper that the AI Safety Working Group is currently writing.
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MLOps Threat Model
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Oct
30
Thu, October 30, 9:00am - 10:00am PDT
AI Safety Working Group Meeting
See details
This is a meeting for the entirety of the AI Safety Working Group. The topics will vary, but largely we will talk about what's going on within the working group, how to participate, and other relevant news/topics pertaining to our AI Safety research.
Currently we meet once a month on the Last Thursday, 9am-10am Pacific Time.
If this time does not work well for you, please let us know. We are considering having a second once-monthly time slot to accommodate the greatest number of folks possible.
Useful links:
Currently we meet once a month on the Last Thursday, 9am-10am Pacific Time.
If this time does not work well for you, please let us know. We are considering having a second once-monthly time slot to accommodate the greatest number of folks possible.
Useful links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Nov
10
Mon, November 10, 9:15am - 10:00am PST
MCP Threats & Enterprise Adoption Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MCP Threats & Enterprise Adoption whitepaper that the AI Safety Working Group is currently writing.
We meet every other Monday at 9:15am Pacific Time.
Useful links:
We meet every other Monday at 9:15am Pacific Time.
Useful links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MCP
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Nov
12
Wed, November 12, 10:00am - 11:00am PST
MCP Security Working Group
See details
Agenda:
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
- CSA events & announcements
- Demo of finder and auditor for MCP server
- Feedback to improve tools
Resources
- Github: https://github.com/modelcontextprotocol-security
- Website: https://modelcontextprotocol-security.io/
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
Nov
13
Thu, November 13, 8:30am - 9:00am PST
MLOps Threat Model Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MLOps Threat Model whitepaper that the AI Safety Working Group is currently writing.
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MLOps Threat Model
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Nov
24
Mon, November 24, 9:15am - 10:00am PST
MCP Threats & Enterprise Adoption Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MCP Threats & Enterprise Adoption whitepaper that the AI Safety Working Group is currently writing.
We meet every other Monday at 9:15am Pacific Time.
Useful links:
We meet every other Monday at 9:15am Pacific Time.
Useful links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MCP
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Nov
26
Wed, November 26, 10:00am - 11:00am PST
MCP Security Working Group
See details
Agenda:
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
- CSA events & announcements
- Demo of finder and auditor for MCP server
- Feedback to improve tools
Resources
- Github: https://github.com/modelcontextprotocol-security
- Website: https://modelcontextprotocol-security.io/
Join Zoom Meeting
https://zoom.us/j/202373686
Meeting ID: 202 373 686
One tap mobile
+16699009128,,202373686# US (San Jose)
+16465588656,,202373686# US (New York)
Dial by your location
+1 669 900 9128 US (San Jose)
+1 646 558 8656 US (New York)
Meeting ID: 202 373 686
Find your local number: https://zoom.us/u/aeuZDvhgcS
Nov
27
Thu, November 27, 8:30am - 9:00am PST
MLOps Threat Model Working Session - CSA AI Safety WG
See details
This is a working session to sync on the MLOps Threat Model whitepaper that the AI Safety Working Group is currently writing.
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
We meet every other Thursday at 8:30am Pacific Time.
Useful Links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- White Paper Draft Folder: Draft - MLOps Threat Model
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Nov
27
Thu, November 27, 9:00am - 10:00am PST
AI Safety Working Group Meeting
See details
This is a meeting for the entirety of the AI Safety Working Group. The topics will vary, but largely we will talk about what's going on within the working group, how to participate, and other relevant news/topics pertaining to our AI Safety research.
Currently we meet once a month on the Last Thursday, 9am-10am Pacific Time.
If this time does not work well for you, please let us know. We are considering having a second once-monthly time slot to accommodate the greatest number of folks possible.
Useful links:
Currently we meet once a month on the Last Thursday, 9am-10am Pacific Time.
If this time does not work well for you, please let us know. We are considering having a second once-monthly time slot to accommodate the greatest number of folks possible.
Useful links:
- Zoom Meeting Link: https://csaurl.org/ai-safety-call
- CSA Public Slack: https://csaurl.org/csa-public-slack
- Working Group Slack Channel: #wg-ai-safety
Open Peer Reviews
Peer reviews allow security professionals from around the world to provide feedback on CSA research before it is published.
Premier AI Safety Ambassadors
Premier AI Safety Ambassadors play a leading role in promoting AI safety within their organization, advocating for responsible AI practices and promoting pragmatic solutions to manage AI risks. Contact [email protected] to learn how your organization could participate and take a seat at the forefront of AI safety best practices.