Explore cutting-edge research on explainable and robust algorithms for privacy-preserved federated learning in future networks in this 15-minute IEEE conference talk. Delve into the SHERPA project, which focuses on developing advanced techniques to enhance privacy, security, and transparency in distributed machine learning systems. Gain insights into the challenges and solutions for implementing federated learning across diverse network environments while maintaining data privacy and model interpretability.
SHERPA: Explainable Robust Algorithms for Privacy-Preserved Federated Learning in Future Networks
Overview
Syllabus
601 SHERPA Explainable Robust Algorithms for Privacy Preserved Federated Learning in Future Networks
Taught by
IEEE Symposium on Security and Privacy
Tags
Related Courses
-
Artificial Intelligence Privacy and Convenience
-
Distributed Optimization and Machine Learning
-
Federated Learning in Big Data Over Networks
-
Fundamentals of Privacy-Preserving Federated Learning
-
Preserving Data Privacy in Federated Learning - Xiaokui Xiao
4.0 -
LOKI: Large-Scale Data Reconstruction Attack Against Federated Learning Through Model Manipulation - 2024
