Low Cost High Power Membership Inference Attacks
Offered By: Google TechTalks via YouTube
Course Description
Overview
Explore a Google TechTalk on membership inference attacks (MIA) in machine learning, presented by Reza Shokri. Delve into the innovative RMIA algorithm, designed for efficient and robust detection of training data usage in ML models. Learn how this novel approach outperforms existing methods in accuracy and computational efficiency, even under limited resources. Discover the importance of stress testing MIA techniques for practical privacy risk assessment. Gain insights into the groundbreaking potential of RMIA for reliable data privacy analysis in machine learning applications.
Syllabus
Low Cost High Power Membership Inference Attacks
Taught by
Google TechTalks
Related Courses
Introduction to Artificial IntelligenceStanford University via Udacity Natural Language Processing
Columbia University via Coursera Probabilistic Graphical Models 1: Representation
Stanford University via Coursera Computer Vision: The Fundamentals
University of California, Berkeley via Coursera Learning from Data (Introductory Machine Learning course)
California Institute of Technology via Independent