Security and Privacy in Agentic AI: Grand Challenges and Future Directions

2026-07-07

AI Summary

This study addresses the emerging risks posed by autonomous decision-making AI agents in the domains of safety and privacy. Bringing together 30 international experts from academia, industry, and government, the project employs horizon-scanning methodology for the first time in this context, integrated with a multi-stakeholder collaborative deliberation framework, to systematically identify and define the core challenges in the field. Grounded in cross-disciplinary expert consensus, the work proposes the first forward-looking, holistic research agenda specifically tailored to the governance of safety and privacy in autonomous AI agents, offering a clear, anticipatory, and actionable pathway to guide future scholarly and policy-oriented inquiry.

Abstract

We present key challenges and future research directions in the security and privacy of agentic AI, based on a horizon-scanning exercise that brought together thirty leading international experts from academia, industry, and government to engage in focused discussions and collaborative exercises on the emerging risks associated with the growing agency of AI.

Problem

• Security
• Privacy
• Agentic AI
• AI Agency
• Emerging Risks

Innovation

• Agentic AI
• Security
• Privacy
• Horizon Scanning
• AI Governance