Protecting Models Trained by Multi-party Learning with Differential Privacy
Security researchers examine technical aspects of Protecting Models Trained by Multi-party Learning with Differential Privacy.
Summary
No summary yet — watch the video above, or open it on YouTube.
Related talks
IEEE Symposium on Security and Privacy·18 min
Analysts investigate attack surfaces and defenses concerning Helen: Maliciously Secure Coopetitive Learning for Linear Models.
helenmaliciouslycoopetitive+3
IEEE Symposium on Security and Privacy·13 min
Generative Models
Presenters detail vulnerability discovery and exploitation in Learning Universal Adversarial Perturbations with Generative Models.
learninguniversaladversarial+3
Eye on Tech·4 min
Industry experts analyze emerging threats surrounding 7 Steps to Build a Machine Learning Model.
machine-learningstepbuild+3