Differential Privacy Preservation in Deep Learning: Challenges, Opportunities and Solutions
Year: 2019
Type: article
Abstract: Nowadays, deep learning has been increasingly applied in real-world scenarios involving the collection and analysis of sensitive data, which often causes privacy leakage. Differential privacy is widely recognized in the majority of traditional scenarios for its rigorous mathematical guarantee. However, it is uncertain to work effectively in the deep learning model. In this paper, we introduce the privacy attacks facing the deep learning model and present them from three aspects: membership inference, training data extraction, and model extracting. Then we recall some basic theory about differential privacy and its extended concepts in deep learning scenarios. Second, in order to analyze the existing works that combine differential privacy and deep learning, we classify them by the layers differential privacy mechanism deployed, such as input layer, hidden layer, and output layer, and discuss their advantages and disadvantages. Finally, we point out several key issues to be solved and provide a broader outlook of this research direction.
Source: IEEE Access
Authors: Jingwen Zhao, Yunfang Chen, Wei Zhang
Institution: Nanjing University of Posts and Telecommunications
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $1,750
Award: G7058848123
OpenAlex ID: W2942094298
