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

arXiv:2609.02971 · cs.CR, cs.LG, cs.NI · Submitted 2026-09-02 · Read on arXiv

cs.CR, cs.LG, cs.NI

Submitted: 2026-09-02

Updated: 2026-09-05

Comments: Accepted for presentation at IEEE VTC2026-Fall, Boston, MA, USA, September 6-9, 2026

Code: https://github.com/aliakarma/PPFL-Sensors

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

Accuracy — 27× in this paper · explained in 1 episode
Federated Learning — 12× in this paper · explained in 15 episodes
Aggregation — 4× in this paper · explained in 1 episode
Benchmark — 4× in this paper · explained in 2 episodes
Agentic AI — 3× in this paper · explained in 1 episode
Differential Privacy — 3× in this paper · explained in 4 episodes
Federated Learning (FL) — 3× in this paper · explained in 7 episodes
Non-IID Data — 3× in this paper · explained in 2 episodes
Differentially Private — 2× in this paper · explained in 3 episodes
Digital Twin — 2× in this paper · explained in 5 episodes
Normalized Attacker Advantage — 2× in this paper
Privacy Score — 2× in this paper
Ablation — 1× in this paper · explained in 1 episode
Agentic AI Framework — 1× in this paper · explained in 1 episode
Core — 1× in this paper · explained in 2 episodes
Cosine Similarity — 1× in this paper · explained in 3 episodes
Edge Deployment — 1× in this paper · explained in 2 episodes
Robustness — 1× in this paper · explained in 5 episodes
Symposium on Security and Privacy — 1× in this paper
Trace — 1× in this paper · explained in 2 episodes
UCI Human Activity Recognition — 1× in this paper

Related papers