Key protected classification for collaborative learning
Date
2020Source Title
Pattern Recognition
Print ISSN
0031-3203
Publisher
Elsevier
Volume
104
Pages
1 - 13
Language
English
Type
ArticleItem Usage Stats
50
views
views
3
downloads
downloads
Abstract
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/mbsariyildiz/key-protected-classification.
Keywords
Privacy-preserving machine learningCollaborative learning
Classification
Generative adversarial networks