SecureDrive-FL Framework for Federated Driver Monitoring
SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring
SecureDrive-FL provides essential protection against both model poisoning and MitM attacks in driver monitoring systems with minimal performance impact.
SecureDrive-FL combines DP-SGD with GASHE encryption for federated driver monitoring.
It achieves 73.6% accuracy on distracted driver classification tasks under non-IID federated splits.
The framework maintains poisoning resistance while withstanding MitM interception, where DP-SGD alone drops to 10.
4% accuracy.It operates with only 8-10% additional runtime overhead compared to DP-SGD alone.
SecureDrive-FL: Joint Differential Privacy and Gradient-Aware Selective Homomorphic Encryption for Federated Driver Monitoring
Federated Learning (FL) enables privacy-aware distributed training, yet gradient updates remain exploitable: Man-in-the-Middle (MitM) interception exposes updates in transit, while model poisoning corrupts global convergence. We first introduce GASHE (Gradient-Aware Selective Homomorphic Encryption), a novel selective encryption strategy that dynamically identifies and encrypts only the gradient components exceeding a DP-calibrated sensitivity threshold, rather than encrypting all parameters uniformly as in static layer-based or full-parameter CKKS schemes. Building on GASHE, we introduce SecureDrive-FL, a federated driver monitoring framework that couples DP-SGD with GASHE to create the first closed-loop DP+HE privacy pipeline: DP-SGD calibration parameters directly derive the GASHE encryption mask, unifying training-time privacy and communication-time confidentiality. Evaluated on a ten-class distracted driver classification task under non-IID federated splits, SecureDrive-FL matches DP-SGD alone's poisoning resistance (73.6% vs. 74.0% accuracy, 3.9% Attack Success Rate for both) while additionally withstanding MitM interception, where DP-SGD alone collapses to near-random accuracy (78.2% vs. 10.4%), all under only approx. 8--10% additional runtime overhead relative to DP-SGD alone---under DP-SGD noise injection with per-round privacy parameter epsilon_0=4.
This report is categorized under AITOP's "Papers" desk. Key entities and technical topics under continuous tracking include SecureDrive-FL, GASHE, DP-SGD, federated learning.
Source attribution: curated from arXiv cs.LG (@Baran Can Gül, Hanuma Siddhartha Tunuguntla, Anjana Arvind Naik, Abhishek Vijay Potekar, Nasser Jazdi, Michael Weyrich).
