YoVDO

Reconstructing Training Data with Informed Adversaries

Offered By: IEEE via YouTube

Tags

IEEE Symposium on Security and Privacy Courses Machine Learning Courses Data Security Courses Data Privacy Courses

Course Description

Overview

Explore the critical topic of training data reconstruction by informed adversaries in this 20-minute IEEE conference talk. Delve into the research presented by experts from DeepMind and the Alan Turing Institute as they discuss potential vulnerabilities in machine learning models and the implications for data privacy and security. Gain insights into the methods used by adversaries to reconstruct training data and understand the challenges faced by researchers in protecting sensitive information. Learn about cutting-edge techniques and strategies being developed to mitigate these risks and safeguard machine learning systems against sophisticated attacks.

Syllabus

Reconstructing Training Data with Informed Adversaries


Taught by

IEEE Symposium on Security and Privacy

Tags

Related Courses

Sensor Security
IEEE via YouTube
Tracking Ransomware End-to-end
IEEE via YouTube
Cinderella - Turning Shabby X.509 Certificates into Elegant Anonymous Credentials with the Magic of Verifiable Computation
IEEE via YouTube
Algorithmic Transparency via Quantitative Input Influence - Theory and Experiments with Learning Systems
IEEE via YouTube
Bitcoin Over Tor Isn't a Good Idea
IEEE via YouTube