mlsanityData to 14 Oct 2026

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

arXiv 2606.11556 ↗First posted 10 Jun 2026cs.CR cs.AI cs.LGcited by 0

Not on the map. Why?

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.

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

18 of 45 references.

References · 18

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,305
  2. 2016Communication-Efficient Learning of Deep Networks from Decentralized Datacited by 7,669
  3. 2016Deep Learning with Differential Privacycited by 2,728
  4. 2018Group Normalizationcited by 1,524
  5. 2017Renyi Differential Privacycited by 650
  6. 2018Quantizing deep convolutional networks for efficient inference: A whitepapercited by 521
  7. 2021Opacus: User-Friendly Differential Privacy Library in PyTorchcited by 383
  8. 2020Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XLcited by 158
  9. 2023How to DP-fy ML: A Practical Guide to Machine Learning with Differential Privacycited by 153
  10. 2021Designing ECG Monitoring Healthcare System with Federated Transfer Learning and Explainable AIcited by 26
  11. 2022Application of federated learning techniques for arrhythmia classification using 12-lead ECG signalscited by 9
  12. 2022Anomaly Detection through Unsupervised Federated Learningcited by 8
6 more
  1. 2025Linkage Attacks Expose Identity Risks in Public ECG Data Sharingcited by 4
  2. 2024Federated Learning and Differential Privacy Techniques on Multi-hospital Population-scale Electrocardiogram Datacited by 3
  3. 2024Privacy-Preserving ECG Data Analysis with Differential Privacy: A Literature Review and A Case Studycited by 2
  4. 2024Enhanced Federated Anomaly Detection Through Autoencoders Using Summary Statistics-Based Thresholdingcited by 2
  5. 2025Federated Learning with Gramian Angular Fields for Privacy-Preserving ECG Classification on Heterogeneous IoT Devicescited by 2
  6. 2025An Attention-Augmented VAE-BiLSTM Framework for Anomaly Detection in 12-Lead ECG Signalscited by 1

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2026BiFedKD: Bidirectional Federated Knowledge Distillation Framework for Non-IID and Long-Tailed ECG Monitoring
  2. 2026Towards Family-Grouped Hierarchical Federated Learning on Sub-5KB Models: A Feasibility Study of Privacy-Preserving ECG Monitoring for Ultra-Resource-Constrained Wearables
  3. 2021Hierarchical Federated Learning based Anomaly Detection using Digital Twins for Smart Healthcare
  4. 2026Membership Inference Attacks Expose Participation Privacy in ECG Foundation Encoders
  5. 2025Enhancing ECG Classification Robustness with Lightweight Unsupervised Anomaly Detection Filters
  6. 2026FedDP-PALD: A Privacy-Preserving Federated Latent Diffusion Framework with Prototype Aggregation for Medical Data Synthesis
  7. 2024Personalized Heart Disease Detection via ECG Digital Twin Generation
  8. 2026ArrythML: An Autoencoder-Based TinyML Approach for On-Device Arrhythmia Detection on Resource-Constrained Embedded Systems