Securing Agentic AI with Context Graphs
Join us for a tech talk on securing AI agents in real-world enterprise systems.
This session explores why traditional identity and access controls fall short when autonomous AI agents can invoke tools, access resources, and delegate work across systems. It introduces context graphs—a practical way to model agent identities, permissions, tools, MCP servers, resources, and delegation paths—so security teams can evaluate the complete chain of activity instead of reviewing each API call in isolation. The talk covers excessive agency, privilege chaining, MCP tool poisoning, lateral movement, and graph-aware policy enforcement. A live Java demonstration will walk through three scenarios: a legitimate request, a blocked privilege-escalation attempt, and a risky multi-hop path that traditional access controls would allow.
💡 Practical security patterns for agentic AI
🖥️ Live policy-engine demonstration
💬 Interactive audience Q&A
Open to engineers, architects, security professionals, students, and anyone interested in building and governing secure AI agents. Register soon!
Date and Time
Location
Hosts
Registration
-
Add Event to Calendar
Loading virtual attendance info...
- Contact Event Hosts
- Co-sponsored by Central Indiana IEEE Computer Society
- Starts 23 August 2026 04:00 AM UTC
- Ends 25 September 2026 04:00 AM UTC
- No Admission Charge
Speakers
Biography:
Rajesh Purushothaman is an identity and cloud security leader with extensive experience building large-scale identity platforms, authentication services, and enterprise security architectures. His work includes supporting identity-cloud migrations for more than 200,000 enterprise tenants and developing security capabilities for modern cloud environments.
His expertise spans identity and access management, cloud security, distributed systems, zero-trust architecture, and agentic AI security. His current work explores how contextual authorization, delegated identity, least-privilege controls, and graph-based analysis can help organizations safely govern autonomous AI agents.
Rajesh is an inventor on four granted U.S. patents. He is a Senior Member of IEEE, Fellow of BCS, Fellow of IETE, Distinguished Fellow of SCRS. He regularly contributes to the technology community as an author, speaker, reviewer, and conference leader, translating emerging security concepts into practical solutions for enterprise AI and cloud systems.