Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcare

Matei Grama, Maria Musat, Luis Muñoz-González, Jonathan Passerat-Palmbach, Daniel Rueckert, Amir AlansaryarXiv 2020 · arXiv

Abstract

This paper explores the intersection of privacy-preserving techniques, such as Differential Privacy (DP) and $k$-anonymity, and Byzantine-robust aggregation methods in Federated Learning (FL) for healthcare. The authors demonstrate that adaptive aggregation methods, specifically Adaptive Federated Averaging (AFA), can successfully detect and block malicious clients without sacrificing model accuracy, even when strict privacy-preserving noise is injected into the system.

Introduction

Federated Learning (FL) is highly attractive for healthcare because it allows multiple hospitals to collaboratively train deep learning models without sharing raw, sensitive patient data, ensuring compliance with regulations like HIPAA and GDPR. However, standard FL aggregation methods, such as Federated Averaging (FedAvg), are highly vulnerable to "poisoning" attacks from faulty or malicious clients.

While robust aggregation methods exist to filter out bad updates, and privacy methods exist to protect patient data, combining them presents a unique challenge. Privacy methods inherently inject noise or generalize data, which can confuse robust aggregation algorithms that rely on measuring the distance or similarity between client updates to spot anomalies. This paper investigates whether a system can be robust to bad actors while simultaneously providing mathematical guarantees for patient privacy.

Methods and Datasets

The authors evaluate three robust aggregation methods:

  • Coordinate-wise Median (COMED): Resists outliers by taking the median of client parameters.
  • Multi-Krum (MKRUM): Aggregates only the models closest to each other in Euclidean space.
  • Adaptive Federated Averaging (AFA): Uses a Hidden Markov Model to track client behavior over time and dynamically block divergent clients.

These methods are combined with two privacy techniques:

  • Differential Privacy (DP): Adds Laplacian noise to 10% of trained model parameters.
  • $k$-anonymity: Generalizes quasi-identifying attributes so no record is distinguishable from at least $k-1$ others.

Experiments were conducted on two tabular healthcare datasets: the Pima Indians Diabetes Dataset (768 records, 10 clients) and the Cleveland Heart Disease Database (297 records, 5 clients).

Results and Discussion

A major takeaway is that privacy-preserving noise does not inherently destroy the ability of algorithms to detect malicious clients. The "signal" of a malicious attack often remains detectable despite the noise introduced by DP or $k$-anonymity.

Error rates for Experiment I (Diabetes) with malicious and faulty clients.

In Experiment I (Diabetes), under DP with three bad clients, standard FedAvg diverged completely. MKRUM and AFA performed best, with AFA successfully detecting and blocking malicious clients when using $k$-anonymity.

Error rates for Experiment II (Heart Disease) with malicious and faulty clients.

In Experiment II (Heart Disease), which featured a smaller dataset, AFA and COMED achieved low error rates (~9%) despite attacks. However, MKRUM failed to learn effectively in this scenario. A critical finding was that $k$-anonymity caused all aggregation methods to fail on this smaller dataset, highlighting that syntactic privacy approaches require a critical mass of data to be effective.

Conclusion

The study confirms that adaptive robust aggregation, particularly AFA, can maintain model integrity in the presence of both malicious actors and privacy-preserving noise. While $k$-anonymity shows limitations on small datasets, Differential Privacy remains a robust option. Future work will explore hyperparameter optimization for AFA and its application to high-dimensional medical imaging tasks.

Summary updated

Abstract

Federated learning (FL) has enabled training models collaboratively from multiple data owning parties without sharing their data. Given the privacy regulations of patient's healthcare data, learning-based systems in healthcare can greatly benefit from privacy-preserving FL approaches. However, typical model aggregation methods in FL are sensitive to local model updates, which may lead to failure in learning a robust and accurate global model. In this work, we implement and evaluate different robust aggregation methods in FL applied to healthcare data. Furthermore, we show that such methods can detect and discard faulty or malicious local clients during training. We run two sets of experiments using two real-world healthcare datasets for training medical diagnosis classification tasks. Each dataset is used to simulate the performance of three different robust FL aggregation strategies when facing different poisoning attacks. The results show that privacy preserving methods can be successfully applied alongside Byzantine-robust aggregation techniques. We observed in particular how using differential privacy (DP) did not significantly impact the final learning convergence of the different aggregation strategies.
BibTeX
@misc{grama2020robust,
  author = {Matei Grama and Maria Musat and Luis Muñoz-González and Jonathan Passerat-Palmbach and Daniel Rueckert and Amir Alansary},
  title = {{Robust Aggregation for Adaptive Privacy Preserving Federated Learning in Healthcare}},
  year = {2020},
  eprint = {2009.08294},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2009.08294},
}
Figure