ChaptersEventsBlog
How is your enterprise using AI Agents? Help us benchmark security and take the survey before November 30 →

Working Group

CAVEaT™

The Joint CSA-MITRE Cloud Adversarial, Vectors, and Threats (CAVEaT) Collaboration to develop, curate, and host a cloud specific threat model to assist Cloud Security practitioners with threat-based analysis.
Cloud Adversarial Vectors, Exploits, and Threats (CAVEaT™): An Emerging Threat Matrix for Industry Collaboration
Cloud Adversarial Vectors, Exploits, and Threats (CAVEaT™): An Emerging Threat Matrix for Industry Collaboration

Download

CSA and the MITRE Corporation have established the Cloud Adversarial, Vectors, Exploits, and Threats (CAVEaT) collaboration to develop, curate, and host cloud specific threat models to assist Cloud Security practitioners with threat-based analysis.

Working Group Leadership

Kurt Seifried
Kurt Seifried

Kurt Seifried

Chief Innovation Officer, CSA

For over two decades, Kurt has excelled in information security, starting with Windows and Linux, and advancing to cloud computing and AI. With a strong focus on AI security, privacy, and open source, Kurt brings extensive expertise to the Cloud Security Alliance (CSA).

Read more

Dr. Mari Spina
Dr. Mari Spina

Dr. Mari Spina

Sr. Principal Cybersecurity Engineer / Cloud Security Capability Leader at MITRE

Dr. Spina joined MITRE in 2014 and has been supporting a multitude of MITRE Federal sponsors including DHS, DoD and the IC in the area of Cloud Security. At MITRE, she is a Principle Cybersecurity Engineer, leads the Cloud Security Capability Area, and teaches Cloud Security for the MITRE Institute. She has also taught many Information Technology courses for the George Washington University schools of engineering and business. Before joini...

Read more

Publications in ReviewOpen Until
Standards-Benchmarks-MaturityDec 13, 2025
Open Source Red Teaming Tool: PyRIT Automation Capability in Agentic Red Team Testing EnvironmentsDec 13, 2025
Using Zero Trust Against Identity Spoofing and AbuseDec 20, 2025
Using Zero Trust to Secure Enterprise Information in LLM EnvironmentsDec 20, 2025
View all
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.

Open Peer Reviews

Peer reviews allow security professionals from around the world to provide feedback on CSA research before it is published.

Learn how to participate in a peer review here.

Standards-Benchmarks-Maturity

Open Until: 12/13/2025

Standardization serves as a foundational backbone that enables uniqueness and diversity to flourish within structured envir...

Open Source Red Teaming Tool: PyRIT Automation Capability in Agentic Red Team Testing Environments

Open Until: 12/13/2025

This paper presents an open source red teaming tool for simulating adversarial attacks in modern systems. Designed for secu...

Using Zero Trust Against Identity Spoofing and Abuse

Open Until: 12/20/2025

The shift towards zero trust architectures brings in a heightened focus on the integrity of identity and identity attribute...

Using Zero Trust to Secure Enterprise Information in LLM Environments

Open Until: 12/20/2025

Guidance for safe enterprise enablement of AI/ML apps while protecting sensitive organizational information (IP, PII, etc.)...