Explore the practical applications of red teaming in the context of AI systems. Led by experts from Microsoft’s AI Red Team, the module will provide insight into identifying and mitigating vulnerabilities within AI models, training data, and deployment environments. Attendees will learn how red teaming helps surface risks, challenge assumptions, and build more secure AI-powered systems.

The AI Learning Series, presented by the WiCyS global team and the AI Affiliate, is a comprehensive program designed to equip cybersecurity professionals with the knowledge and skills needed to navigate the evolving landscape of artificial intelligence. The series features six, 90-minute modules led by industry experts, covering topics from AI fundamentals and their intersection with cybersecurity to risks, governance, and secure AI product development. Participants will gain insights into building secure AI products, securing third-party AI/ML solutions, leveraging AI to enhance organizational and customer security, and understanding AI policy and regulations.