Publications & Contributions
Papers, talks, and standards work on architecting and securing production AI systems.
Research, Books & Whitepapers
Bounded Agents: Delegation Security for Multi-Agent AI Systems
arXiv:2608.15888 · Author · 2026
The Agentic Principal Chain (APC) model with blast radius monotonicity, composition soundness, and intent binding for LLM-based agentic systems.
Read more
AI Security Engineering
ForthcomingO'Reilly Media · Technical Reviewer
Reviewing security architecture, threat models, controls, and secure production AI practices.
Defending at Machine Speed, After Mythos
AIUC-1 Consortium Whitepaper · Co-Author · 2026
AIUC-1 Consortium whitepaper on defensive AI security practices for machine-speed threats.
Read moreEngineering a Culture of AI Security
AIUC-1 Consortium Whitepaper · Co-Author · 2026
AIUC-1 Consortium whitepaper on building the organizational practices and engineering culture that make AI security a default outcome of how teams build, not a control added afterward.
Read more
State of Agentic AI Security and Governance
OWASP GenAI Security Project · Expert Reviewer · 2026
OWASP GenAI Security Project report on the current state of agentic AI security and governance practices across the industry.
Read moreThe End of Vibe Adoption
AIUC-1 Consortium Whitepaper · Co-Author · 2025
Consortium whitepaper on moving beyond unstructured AI adoption toward governed, evidence-backed production deployment with 50 leaders across industry and academia.
Read morePerspectives & Explainers
Agentic AI Security
muruaga.ai · Author
The agentic AI attack surface, the architectural controls that hold up in production, and where authorization and delegation security fit.
Read moreAI Agent Authorization
muruaga.ai · Author
Why per-request authorization breaks down for AI agents, what a sufficient model needs, and a concrete architecture that implements it.
Read moreTalks & Technical Content
Scalable AI Adoption at Iberdrola
AWS Summit Madrid 2025 · May 2025
Reference architecture and operating model for production AI across a multi-cloud enterprise: shared entry points, cost attribution, onboarding standards, and governance.
Read moreAgentic AI at Iberdrola with Amazon Bedrock AgentCore
AWS Machine Learning Blog · 2025
Co-authored technical blog on architecture and controls for agentic AI in production: governed tool access, scoped identity, managed memory, runtime budgets, and approval boundaries.
Read moreLectures
AI Systems — Architecture, Security & Production Assurance
IE University — Master in Business Analytics & Data Science · 2025 – Present
Adjunct Professor. Course covering production-grade AI system design, governance, security, and operation at scale.
AI Security & Secure AI Adoption for Founders
Mondragon Unibertsitatea — Master in Entrepreneurship & Open Innovation · 2024 – Present
Guest lectures on GenAI risk, AI security, and how to design, govern, and scale AI-enabled products safely.
Standards & Frameworks
GenAI Security Project
OWASP Foundation · Contributor
Contributing to GenAI and Agentic AI security, with a focus on authorization, runtime policy enforcement, threat modeling, and agent identity & delegation.
AI Safety Working Group
Cloud Security Alliance · Member
Contributing to practical guidance on AI threat modeling, security controls, and risk frameworks for enterprise AI, LLM, and agentic systems.
AIUC-1 Consortium
AIUC-1 · Founding Consortium Member
Founding member contributing to agentic AI security, governance, assurance, and safe production deployment.