Federated Black-Box Adaptation for Semantic Segmentation

TL;DR

This paper introduces BlackFed, a privacy-preserving federated learning framework for semantic segmentation that avoids sharing gradients or model architecture details, using zero order and first order optimization techniques.

Contribution

It presents a novel black-box federated learning approach for segmentation that enhances privacy by eliminating gradient and model information exchange.

Findings

Effective on multiple datasets for computer vision and medical imaging

Outperforms existing methods in privacy preservation

Demonstrates feasibility of gradient-free federated segmentation

Abstract

Federated Learning (FL) is a form of distributed learning that allows multiple institutions or clients to collaboratively learn a global model to solve a task. This allows the model to utilize the information from every institute while preserving data privacy. However, recent studies show that the promise of protecting the privacy of data is not upheld by existing methods and that it is possible to recreate the training data from the different institutions. This is done by utilizing gradients transferred between the clients and the global server during training or by knowing the model architecture at the client end. In this paper, we propose a federated learning framework for semantic segmentation without knowing the model architecture nor transferring gradients between the client and the server, thus enabling better privacy preservation. We propose BlackFed - a black-box adaptation of neural networks that utilizes zero order optimization (ZOO) to update the client model weights and first order optimization (FOO) to update the server weights. We evaluate our approach on several computer vision and medical imaging datasets to demonstrate its effectiveness. To the best of our knowledge, this work is one of the first works in employing federated learning for segmentation, devoid of gradients or model information exchange. Code: https://github.com/JayParanjape/blackfed/tree/master