ASCEND
BY NTHRYS

NTHRYS › PhD Assistance › Data Ethics Privacy Studies

Data Ethics Privacy Studies

Field
▾
Category
▾

Data Ethics Privacy Studies

Select a category to explore research frontiers

Loading categories...

Research Frontiers in Federated Learning Privacy Vulnerabilities

Analyzes privacy threats including membership inference and gradient inversion attacks in decentralized collaborative machine learning.

Gradient Leakage in Decentralized Neural Networks
Membership Inference Across Federated Model Boundaries
Poisoning Attacks in Collaborative Learning Architectures
Privacy-Utility Frontiers in Distributed Training
Model Inversion Through Federated Aggregation Patterns
Differential Privacy Composition in Multi-Round Protocols
Backdoor Persistence in Federated Learning Systems
Cross-Silo Privacy Leakage in Heterogeneous Data
Reconstruction Attacks on Compressed Federated Updates
Byzantine Robustness and Privacy Trade-offs

All Data Ethics & Privacy Studies PhD categories