# Privacy-Preserving Federated Autoencoder for ECG Anomaly Detection on Edge Devices

arXiv: https://arxiv.org/abs/2606.11556 · HTML: https://mlsanity.com/paper/2606.11556/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 18 of its 45 references that are in the map.
- First posted on arXiv 10 Jun 2026.

## Builds on (most cited first, 18 of 18)

- [PyTorch: An Imperative Style, High-Performance Deep Learning Library](https://mlsanity.com/paper/1912.01703/) (2019)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Group Normalization](https://mlsanity.com/paper/1803.08494/) (2018)
- [Renyi Differential Privacy](https://mlsanity.com/paper/1702.07476/) (2017)
- [Quantizing deep convolutional networks for efficient inference: A whitepaper](https://mlsanity.com/paper/1806.08342/) (2018)
- [Opacus: User-Friendly Differential Privacy Library in PyTorch](https://mlsanity.com/paper/2109.12298/) (2021)
- [Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL](https://mlsanity.com/paper/2004.13701/) (2020)
- [How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacy](https://mlsanity.com/paper/2303.00654/) (2023)
- [Designing ECG Monitoring Healthcare System with Federated Transfer Learning and Explainable AI](https://mlsanity.com/paper/2105.12497/) (2021)
- [Application of federated learning techniques for arrhythmia classification using 12-lead ECG signals](https://mlsanity.com/paper/2208.10993/) (2022)
- [Anomaly Detection through Unsupervised Federated Learning](https://mlsanity.com/paper/2209.04184/) (2022)
- [Linkage Attacks Expose Identity Risks in Public ECG Data Sharing](https://mlsanity.com/paper/2508.15850/) (2025)
- [Federated Learning and Differential Privacy Techniques on Multi-hospital Population-scale Electrocardiogram Data](https://mlsanity.com/paper/2405.00725/) (2024)
- [Privacy-Preserving ECG Data Analysis with Differential Privacy: A Literature Review and A Case Study](https://mlsanity.com/paper/2406.13880/) (2024)
- [Enhanced Federated Anomaly Detection Through Autoencoders Using Summary Statistics-Based Thresholding](https://mlsanity.com/paper/2410.09284/) (2024)
- [Federated Learning with Gramian Angular Fields for Privacy-Preserving ECG Classification on Heterogeneous IoT Devices](https://mlsanity.com/paper/2511.03753/) (2025)
- [An Attention-Augmented VAE-BiLSTM Framework for Anomaly Detection in 12-Lead ECG Signals](https://mlsanity.com/paper/2510.05919/) (2025)

## Abstract (arXiv)

Continuous electrocardiography (ECG) monitoring could surface rhythm abnormalities before they escalate into cardiovascular events. However, a deployable system must satisfy three requirements simultaneously: legal-grade privacy (GDPR, HIPAA), real-time inference on constrained edge hardware, and detection quality under non-IID cross-hospital data. We design and evaluate an end-to-end federated system addressing all three for unsupervised 12-lead ECG anomaly detection on PTB-XL dataset, combining three autoencoder families (VanillaAE, ConvAE, VAE), Flower-based federated averaging (FedAvg) across ten simulated hospitals, client-side differentially private SGD (DP-SGD) with a R'enyi-DP accountant, and 8-bit integer (INT8) post-training quantization with Raspberry Pi 4 benchmarking. Our main contributions are: an empirical characterization of how these mechanisms compose, practical DP-specific recommendations, and technical and security insights for a clinically sensitive setting. Federated learning matches or exceeds the centralized baseline across all architectures (ConvAE federated area under the ROC curve, AUROC, 0.782), and an varepsilon sweep identifies varepsilon=4 as the recommended clinical operating point. INT8 quantization roughly halves model size and cuts Pi 4 latency by up to 44% with <0.12% AUROC loss. Crucially, DP and quantization penalties are empirically independent, so practitioners need not trade a strong privacy guarantee for a compact edge footprint. To our knowledge, this is the first system combining federated learning, formal (varepsilon,δ)-DP, unsupervised reconstruction-based detection, and quantized AArch64 deployment.