Course Websites

Subject offerings of new and developing areas of knowledge in computer science intended to augment the existing curriculum. See Class Schedule or departmental course information for topics and prerequisites. Course Information: May be repeated in the same or separate terms if topics vary.

AI agents and connected devices are rapidly becoming core components of modern computing systems, from enterprise AI platforms to IoT deployments. However, these emerging ecosystems introduce new security risks, including prompt injection, unsafe delegation of authority, and vulnerabilities in IoT software and protocols. This seminar explores the security of open-source ecosystems for AI agents and IoT systems through research discussions and hands-on development. Students will work in teams on real open-source projects in one of two tracks. The AI Agent Security track focuses on developing security enhancements for agent frameworks and communication protocols (e.g., NLIP), such as defenses against prompt injection, secure agent-to-agent communication, and monitoring of agent behavior. The IoT Security Verification track focuses on building and extending an open-source IoT security verification pipeline, where students study state-of-the-art IoT vulnerability detection and verificatio