Key protected classification for collaborative learning

doi:10.1016/j.patcog.2020.107327

2020-08-01

Ramazan Gökberk Cinbiş *

Erman Ayday

DOI：10.1016/j.patcog.2020.107327

原文链接

查看原文

摘要

En 中文

Large-scale datasets play a fundamental role in training deep learning models. However, dataset collection is difficult in domains that involve sensitive information. Collaborative learning techniques provide a privacy-preserving solution, by enabling training over a number of private datasets that are not shared by their owners. However, recently, it has been shown that the existing collaborative learning frameworks are vulnerable to an active adversary that runs a generative adversarial network (GAN) attack. In this work, we propose a novel classification model that is resilient against such attacks by design. More specifically, we introduce a key-based classification model and a principled training scheme that protects class scores by using class-specific private keys, which effectively hide the information necessary for a GAN attack. We additionally show how to utilize high dimensional keys to improve the robustness against attacks without increasing the model complexity. Our detailed experiments demonstrate the effectiveness of the proposed technique. Source code will be made available at https://github.com/mbsariyildizikey-protected-classification. (C) 2020 Elsevier Ltd. All rights reserved.

Keyword:

Privacy-preserving machine learning

collaborative learning

classification

generative adversarial networks