Key protected classification for collaborative learning
作者：
Highlights：
• Collaborative learning allow privacy-preserving training in sensitive domains.
• Collaborative learning is vulnerable to generative adversarial training-based attacks.
• An attack-resilient classification model and principled training scheme is proposed.
• The proposed model prevents active attacks by hiding class scores via class keys.
• How to utilize high-dimensional keys without increasing model complexity is shown.
摘要
•Collaborative learning allow privacy-preserving training in sensitive domains.•Collaborative learning is vulnerable to generative adversarial training-based attacks.•An attack-resilient classification model and principled training scheme is proposed.•The proposed model prevents active attacks by hiding class scores via class keys.•How to utilize high-dimensional keys without increasing model complexity is shown.
论文关键词：Privacy-preserving machine learning,collaborative learning,classification,generative adversarial networks
论文评审过程：Received 31 July 2019, Revised 23 February 2020, Accepted 8 March 2020, Available online 14 March 2020, Version of Record 20 March 2020.
论文官网地址：https://doi.org/10.1016/j.patcog.2020.107327
