A panel discussion focused on the new textbook, Artificial Intelligence Safety and Security.

Panelists include:

• Catherine Olsson (Google Brain): Panel Moderator
• Roman Yampolskiy (The Editor of Artificial Intelligence Safety and Security): Author of Preface: “Introduction to AI Safety and Security”
• Alexey Kurakin (Google AI): First Author of Chapter 8: “Adversarial Examples in the Physical World” with co-authors Ian J. Goodfellow and Samy Bengio
• Phillip Kuznetsov (Machine Learning @ Berkeley): First Author of Chapter 17: “Adversarial Machine Learning” with co-authors Riley Edmunds, Ted Xiao, Humza Iqbal, Raul Puri, Noah Golmant, and Shannon Shih
• Mahendra Prasad (UC Berkeley Political Science): Author of Chapter 21: “Social Choice and the Value Alignment Problem”
• Thomas Gilbert (UC Berkeley Machine Ethics and Epistemology): Panel Discussant

Light refreshments to be served. Attendees are encouraged to bring and eat lunch if they want.