NDC Conferences YouTube · July 29, 2026

Fine-Grained Authorization: The Missing Piece in Agentic AI Security - Shivay Lamba - NDC Sydney

video AI Engineering AI Red Teaming Agent Security

Fine-Grained Authorization: The Missing Piece in Agentic AI Security - Shivay Lamba - NDC Sydney video thumbnail

Why it matters

Shivay Lamba explains how fine-grained, relationship-based authorization can enforce per-user and per-document access in RAG and agent pipelines. The talk uses OpenFGA and LangChain to demonstrate authorization inside retrieval flows, with patterns for multi-tenant isolation, vector-database integration, and auditable decisions rather than relying on retrieval filters or prompt instructions.

My takeaway: Authorize every retrieval and tool action against the current principal, resource, relationship, and context. Model tenant, document, and tool boundaries; deny by default; preserve decision logs; and test cross-tenant access, stale membership, confused-deputy paths, and index synchronization. Never delegate access-control enforcement to the model or its system prompt.

Keep exploring

More curated notes connected through AI Engineering and AI Red Teaming.

OpenAI News · framework

OpenAI’s Frontier Governance Framework

OpenAI's 22-page Frontier Governance Framework maps its frontier-model processes to California's Transparency in Frontier AI Act and the EU AI Act's general-purpose AI code. It documents lifecycle risk assessment, cyber-offense and other risk tiers, mitigation and residual-risk decisions, critical-incident handling, security risk management, model reporting, external review, responsibility allocation, and change control.

OWASP GenAI Security Project · guide

OWASP Top 10 for Agentic Applications for 2026

OWASP's community guide organizes agentic-system risk into ten categories, including goal hijacking, tool misuse, identity and privilege abuse, memory poisoning, insecure inter-agent communication, cascading failures, and rogue-agent behavior. It provides a shared taxonomy and mitigation starting point rather than a certification checklist or evidence that a deployed system is secure.

OECD.AI Wonk · guide

A five-step roadmap to closing the AI evaluation gap

The roadmap addresses evaluation results that overstate real-world performance or fail to transfer across deployment contexts. Its five steps balance standardized and local tests, evaluate throughout the lifecycle, build qualified assurance and communication capacity, tailor tests to each value-chain actor and technology, and use a coordinated, trusted process for updating methods.