Adversarial Testing of AI Systems
As AI systems become more prevalent, they face increasing threats from sophisticated attacks designed to manipulate or extract information from them. This hands-on course equips participants with practical red-team skills to test the adversarial robustness of high-risk AI systems, helping organisations identify vulnerabilities before malicious actors can exploit them.
This course is designed for AI safety and security professionals, red-team testers, compliance officers, risk managers, and technical leads responsible for high-risk AI systems. It is particularly valuable for organisations subject to the EU AI Act or similar regulatory standards.
AI Assurance E-Learning Platform - Self-paced online.
Participants will receive a certificate of completion upon finishing the course.