IEEE Virtual Event! Securing Agentic AI: From Security Risks to Practical Defenses for Autonomous Systems – Oct 22, 2025

Date: Wednesday, October 22, 2025
Time: 05:15 PM PDT to 06:15 PM PDT
Timezone: America/Los Angeles (UTC-8:00)
Location: Zoom and YouTube Live

Agentic AI systems combine autonomy with real-world tool use, offering transformative potential but also introducing novel risks. This talk will introduce agentic AI and outline key vulnerabilities, including jailbreaks, tool hijacking, model misuse, and indirect exploitation through prompt injection. It will then focus on security risks associated with the Model Context Protocol (MCP) and conclude with mitigation strategies and practical defenses to enhance the safety of autonomous AI systems in real-world deployments.

Registration Link: IEEE.org

This content was originally posted on IEEE Computer Society Events directory. This post is shared for student awareness only and does not indicate CGU sponsorship or endorsement.