Welcome

Upcoming Dates

Date	Event	Link
Oct 1, 2025	CA ADS employment regulations effective	Link
Nov 2025	OWASP Top 10 for Agentic Applications release	NA
Nov 2025	OWASP COMPASS v2.0 release	NA
Feb 1 Jun 30, 2026	Colorado AI Act (CAIA) effective	Link
Jan 2026	South Korea AI Act effective	Link
Aug 2, 2026	EU AI Act - full enforcement for high-risk systems	Link

---

View Cheatsheet

---

Recently Added

• [1/7] Two tools: one that scans serialized model artifacts for security issues, and one that generates realistic 3D image augmentations for benchmarking and training.
  • ModelScan
  • 3D Common Corruptions
• [12/12] President Trump's new Executive Order, which seeks to establish a national policy framework for AI in lieu of individual state regulations.
  • Ensuring a National Policy Framework for Artificial Intelligence
• [12/12] The newly released Top 10 list from the GenAI Security Project's Agentic Security Initiative
  • Top 10 for Agentic Applications 2025
• [11/25] The entire ISO/IEC 5259 series on data quality for machine learning and analytics (2024-2025)
  • Part 1: Overview, terminology, and examples
  • Part 2: Data quality measures
  • Part 3: Data quality management requirements and guidelines
  • Part 4: Data quality process framework
  • Part 5: Data quality governance framework
• [11/24] Two tools for AI/ML explainability (XAI)
  • SHAP
  • LIME
• [10/30] Guidance from NIST, OWASP, DHS, and CDAO
  • NIST AI 100-2 E2025 Adversarial Machine Learning: A Taxonomy and Terminology of Attacks and Mitigations
  • Agent Name Service
  • DHS Roles and Responsibilites Framework for AI in Critical Infrastructure
  • CDAO Test & Evaluation of Artificial Intelligence Models
• [10/14] A flagship project from OWASP that consolidates over 200 pages of guidance and references for protecting AI and data-centric systems from threats. Content is actively contributed to international standards.
  • OWASP AI Exchange
• [10/02] A living database of AI incidents, causing harm or near-harm
  • AI Incident Database
• [9/30] Two U.S. Government guidance documents on AI risk and security. One from the Department of Transportation on managing AI risks in transportation systems, and another from CISA, NSA, and FBI on deploying AI securely in enterprise environments.
  • From U.S. DOT: Understanding AI Risks in Transportation
  • From CISA, NSA, FBI, and partners: Deploying AI Systems Securely
• Two older but still relevant ISO standards on AI risk management and bias. See:
  • ISO/IEC 23894:2023 Guidance on risk management
  • ISO/IEC TR 24027:2021 Bias in AI systems