Privacy Leakage in Federated Learning: Gradient-Based Client Identity Inference and Defenses for Inertial Sensing in Vehicular Edge Networks

This paper demonstrates that federated learning systems processing inertial sensor data from vehicles can leak client identity information through gradient analysis, enabling adversaries to infer which devices contributed to model training. The authors propose defense mechanisms including differential privacy and gradient perturbation to mitigate these privacy risks in vehicular edge networks.

This paper demonstrates that federated learning systems processing inertial sensor data from vehicles can leak client identity information through gradient analysis, enabling adversaries to infer which devices contributed to model training. The authors propose defense mechanisms including differential privacy and gradient perturbation to mitigate these privacy risks in vehicular edge networks.

High-quality data pipelines remain the most consistent bottleneck in enterprise AI maturity. QuettaMinds helps clients close the gap between raw data assets and production-ready AI inputs.