Privacy-Preserving Decentralized Federated Learning via Explainable Adaptive Differential Privacy

Decentralized federated learning enables collaborative model training without a central server, but shared model updates can still leak sensitive information through inversion, reconstruction, and membership inference attacks. Differential privacy offers formal protection, yet existing decentralized methods operate without visibility into the noise already injected by previous participants. Each client therefore adds a full, worst-case perturbation at every step, and the accumulated noise degrades accuracy well below what the privacy requirement actually demands. We present PrivateDFL, a decentralized and privacy-preserving framework that pairs hyperdimensional computing with a transparent noise accountant. The accountant tracks the cumulative perturbation present in the shared model and lets each client add only the minimal incremental noise needed to satisfy its privacy budget. We prove that every transmitted model satisfies the target privacy guarantee, and that under this accounting the cumulative noise grows only logarithmically in the number of clients and rounds, rather than the far faster super-linear growth incurred without accounting. This yields a substantially tighter balance between privacy and accuracy than prior approaches. Across image, speech, and wearable-sensor benchmarks, and under both identically and non-identically distributed data, PrivateDFL surpasses centrally trained Transformer-based and deep neural network baselines, improving accuracy by 16 percent on images, 62 percent on speech, and 14 percent on wearable sensing over the strongest baseline in each case, while reducing inference latency by up to 119 times and energy consumption by up to 143 times. These properties make PrivateDFL a practical solution for privacy-preserving collaborative learning in settings where sensitive data cannot be centralized, such as healthcare and human-activity monitoring.