Explore the security challenges of peer-to-peer decentralized machine learning in this 17-minute IEEE conference talk. Delve into the research findings presented by Dario Pasquini, Mathilde Raynal, and Carmela Troncoso from the SPRING Lab at EPFL, Switzerland. Gain insights into the potential vulnerabilities and risks associated with this emerging field of machine learning, and understand the implications for future developments in decentralized AI systems.
On the Insecurity of Peer-to-Peer Decentralized Machine Learning
Overview
Syllabus
On the (In)security of Peer-to-Peer Decentralized Machine Learning
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
IoT Cloud
-
Manipulating Machine Learning - Poisoning Attacks and Countermeasures for Regression Learning
-
SoK - Decentralized Finance - DeFi Attacks
-
CanDID: Bootstrapping Decentralized Identity from Legacy Providers
-
BadEncoder - Backdoor Attacks to Pre-trained Encoders in Self-Supervised Learning
-
Flawed, but Like Democracy We Don't Have a Better System - The Experts' Insights on the Peer Review Process of Evaluating Security Papers
