Explore the cutting-edge field of adversarial machine learning in this 59-minute conference talk presented by Nicholas Carlini from Google Brain. Delivered at the 2nd Deep Learning and Security Workshop during the 2019 IEEE Symposium on Security & Privacy in San Francisco, CA, delve into the challenges and advancements in making and measuring progress in this critical area of AI security. Gain insights into the latest techniques for creating and defending against adversarial examples, and understand the metrics used to evaluate the robustness of machine learning models. Learn from a leading expert in the field as Carlini discusses the intersection of deep learning and security, providing valuable knowledge for researchers, practitioners, and anyone interested in the future of AI safety and reliability.
Making and Measuring Progress in Adversarial Machine Learning
Overview
Syllabus
Nicholas Carlini: Making and Measuring Progress in Adversarial Machine Learning
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
AI Safety – Full Course from Safe.AI on Machine Learning & Ethics
5.0 -
Keras Deep Learning & Generative Adversarial Networks (GAN)
-
Lessons Learned from Evaluating the Robustness of Defenses to Adversarial Examples
-
Defense Against the Dark Arts
-
Distillation as a Defense to Adversarial Perturbations against Deep Neural Networks
-
Stealthy Porn - Understanding Real World Adversarial Images for Illicit Online Promotion
