Home | Posts | Papers | Talks | About
Angles of Attack: Engineering Mission-Critical AI Systems
New | Resources
Real-Time Embedded Systems: A Quick Primer For AI
Systems that must operate in real-time–including AI–are more than just fast, they’re preictable, reliable, and robust. »
AI Systems Vs Mission-Critical Applications
One of the biggest challenges in creating mission-critical AI is baked into the nature of AI/ML systems themselves. »
When Enough Is Enough: Assurance Cases for AI System Security Design
How do we know whether our security and robustness requirements for mission-critical AI systems are good enough? »
Resources
OWASP AI Exchange
The OWASP AI Exchange is an open collaborative project to advance the development of AI security standards and regulations, by providing a comprehensive overview of AI threats, vulnerabilities and controls. Content feeds into standards for the EU AI Act, ISO/IEC 27090 (AI security), the OWASP ML top 10, the OWASP LLM top 10, and OpenCRE. »
OWASP AIX AI Security Overview
The OWASP AI Exchange’s overview of AI security, including helpful introductions to AI threats, mitigations, lifecycles and more. »
The AI Security Matrix
The AI security matrix (graphic) shows all threats and risks, ordered by type and impact. »
NIST AI 100-2e2023 Adversarial Machine Learning
A Taxonomy and Terminology of AI Attacks and Mitigations, prepared by the US National Institute of Standards and Technology. »
AI Security Reference Repository
A Github repo of some of the most influential papers, books, & other media on machine learning operations (MLOps), adversarial machine learning, AIML policy and compliance, ++ »