Securing Agentic AI: From Security Risks to Practical Defenses for Autonomous Systems

Name: Securing Agentic AI: From Security Risks to Practical Defenses for Autonomous Systems
Start: 2025-10-22T17:15:00-07:00
End: 2025-10-22T18:15:00-07:00
Location: Room: MLK Room 225, Dr. Martin Luther King, Jr. Library (SJSU), 150 E San Fernando St San Jose, California 95112, San Jose, California, United States, Virtual: https://events.vtools.ieee.org/m/501651

October 22 @ 5:15 pm - 6:15 pm

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.
Co-sponsored by: Vishnu S. Pendyala, San Jose State University
Speaker(s): Dewank, Dr. Vishnu S. Pendyala
Room: MLK Room 225, Dr. Martin Luther King, Jr. Library (SJSU), 150 E San Fernando St San Jose, California 95112, San Jose, California, United States, Virtual: https://events.vtools.ieee.org/m/501651

Details

Date:: October 22
Time:: 5:15 pm - 6:15 pm
Website:: https://events.vtools.ieee.org/m/501651

Venue

: Room: MLK Room 225, Dr. Martin Luther King, Jr. Library (SJSU), 150 E San Fernando St San Jose, California 95112, San Jose, California, United States, Virtual: https://events.vtools.ieee.org/m/501651