Robust Smart Home Face Recognition under Starving Federated Data

TL;DR

This paper introduces FLATS, a federated adversarial training method for smart home face recognition that enhances model robustness in starving federated environments, addressing limitations of traditional adversarial attacks.

Contribution

The paper proposes a novel federated adversarial training approach called FLATS, specifically designed for smart home face recognition in resource-constrained federated settings.

Findings

FLATS improves global model robustness under starving federated conditions.

Hyperparameter variations significantly affect the effectiveness of federated adversarial training.

The method demonstrates potential for real-world deployment in privacy-sensitive smart home environments.

Abstract

Over the past few years, the field of adversarial attack received numerous attention from various researchers with the help of successful attack success rate against well-known deep neural networks that were acknowledged to achieve high classification ability in various tasks. However, majority of the experiments were completed under a single model, which we believe it may not be an ideal case in a real-life situation. In this paper, we introduce a novel federated adversarial training method for smart home face recognition, named FLATS, where we observed some interesting findings that may not be easily noticed in a traditional adversarial attack to federated learning experiments. By applying different variations to the hyperparameters, we have spotted that our method can make the global model to be robust given a starving federated environment. Our code can be found on https://github.com/jcroh0508/FLATS.