DiPSeN: Differentially Private Self-normalizing Neural Networks For Adversarial Robustness in Federated Learning
arXiv:2101.03218
Abstract
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.
References in corpus (12)
- Deep Learning with Differential Privacy
- Byzantine-Robust Distributed Learning: Towards Optimal Statistical Rates
- Certifying Some Distributional Robustness with Principled Adversarial Training
- Mitigating Adversarial Effects Through Randomization
- Learning with Bad Training Data via Iterative Trimmed Loss Minimization
- IBM Federated Learning: an Enterprise Framework White Paper V0.1
- DeepCloak: Masking Deep Neural Network Models for Robustness Against Adversarial Samples
- Excessive Invariance Causes Adversarial Vulnerability
- On the Effectiveness of Defensive Distillation
- The Threat of Adversarial Attacks on Machine Learning in Network Security -- A Survey
- Exploiting Excessive Invariance caused by Norm-Bounded Adversarial Robustness
- Adversarial Robustness Toolbox v1.0.0