Trustworthy AI in the Era of Generative Models: Security, Fairness, and Reliability

Join our comprehensive Trustworthy Machine Learning webinar exploring the critical foundations of AI system reliability, fairness, and security in the modern AI landscape. This interactive online session covers essential concepts, including model trustworthiness definitions, fairness metrics, robustness techniques, and interpretability methods, with special focus on emerging Generative AI security challenges and vulnerabilities. Participants will gain insights into real-world threats, including adversarial attacks, data poisoning, model inversion, and the unique security risks posed by large language models and generative systems. The webinar addresses both traditional ML trustworthiness issues, such as distribution shifts and bias detection, alongside cutting-edge GenAI concerns like prompt injection, model extraction, and hallucination mitigation strategies. Led by industry experts, this session combines theoretical foundations with practical case studies of ML failures and GenAI security breaches, delivered through interactive polls and live Q&A segments without hands-on coding components.