Establishing the shared foundations for collective AI security

OECD AI Policy Observatory OECD Published: 2026-05-21 07:08:02

AI security, prompt injection, AI agents and model poisoning: building shared foundations for secure AI deployment. The post Establishing the shared foundations for collective AI security appeared fir…

No full content stored. Use “Open Source” to read the original.

Open Source → View topic (Trending) →

Recommended reads

Investors matter for the future of trustworthy AI. Are they ready? From OECD

Investors are beginning to treat trustworthy AI as a material business factor. The challenge now is helping guide capital flows towards firms developing and deploying trustworthy AI. The post Investor…

OECD AI Policy Observatory · OECD 2026-10-12

Bridging frameworks: How HAIP 2.0 supports interoperability with the EU AI Act From OECD

This blog article explores how HAIP 2.0 and the EU instruments intersect, where they diverge, and why their complementarity matters for effective AI governance. The post Bridging frameworks: How HAIP …

OECD AI Policy Observatory · OECD 2026-09-30

Governing with agentic AI: when machines act on government’s behalf From OECD

Agentic AI raises new questions about how governments can maintain standards of safe, secure and trustworthy AI while machines act on their behalf. The post Governing with agentic AI: when machines ac…

OECD AI Policy Observatory · OECD 2026-09-25