Trust and Distrust in ML: Privacy, Verification and Robustness

Explore the critical dimensions of machine learning trustworthiness in this Emmy Noether Lecture by Shafi Goldwasser from the Simons Institute for the Theory of Computing, UC Berkeley, MIT, and Weizmann Institute of Science. Delve into three fundamental challenges facing modern ML systems: privacy concerns, verification requirements, and robustness against adversarial attacks. The hour-long talk examines how these interconnected issues impact the reliability and security of machine learning applications across various domains. Scheduled for April 14, 2025, at 2:00pm in Wolfensohn Hall with remote access options available, this lecture provides valuable insights for researchers, practitioners, and anyone interested in the theoretical foundations of secure and trustworthy artificial intelligence.