DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning
This work is significant for IoT applications requiring secure and private machine learning, as it aims to improve the adversarial robustness of deep learning classifiers in federated learning, which is an incremental improvement for this specific domain.
This paper addresses the challenge of adversarial robustness in federated learning environments by proposing DiPSeN, a Differentially Private Self-normalizing Neural Network. DiPSeN combines differential privacy noise with self-normalizing techniques, and empirical results on three public datasets demonstrate its success in improving adversarial robustness.
The need for robust, secure and private machine learning is an important goal for realizing the full potential of the Internet of Things (IoT). Federated learning has proven to help protect against privacy violations and information leakage. However, it introduces new risk vectors which make machine learning models more difficult to defend against adversarial samples. In this study, we examine the role of differential privacy and self-normalization in mitigating the risk of adversarial samples specifically in a federated learning environment. We introduce DiPSeN, a Differentially Private Self-normalizing Neural Network which combines elements of differential privacy noise with self-normalizing techniques. Our empirical results on three publicly available datasets show that DiPSeN successfully improves the adversarial robustness of a deep learning classifier in a federated learning environment based on several evaluation metrics.