A hybrid deep learning framework for privacy preservation in edge computing. Issue 129 (June 2023)

• Record Type: Journal Article
• Authors: R, Harine Rajashree; K, Sundarakantham; E, Sivasankar; S, Mercy Shalinie
• Is Part Of: Computers & security. Issue 129(2023)
• Publication Date: 2023-06
• Subjects: Internet of things -- Privacy preservation -- Evolutionary algorithm -- Adversarial training -- Deep learning; Computer security -- Periodicals; Electronic data processing departments -- Security measures -- Periodicals; 005.805
• DOI: 10.1016/j.cose.2023.103209
• Languages: English
• ISSNs: 0167-4048

Abstract

Highlights: Data sharing for analytics prone to privacy concerns. Representation of data using deep learning is appropriate to preserve privacy. Representation learning should achieve maximum data usability and privacy. Genetically guided learning balances utility-privacy trade-off. Evaluation of representation learning through compound fitness function is proficient. Abstract: The number of connected devices in our world is continuously increasing at a rapid rate. The Internet of Things(IoT) civilization has resulted in the generation of enormous amounts of data. Analytics on this data pays off in various sectors like health care, manufacturing, and transportation. However, the data generated in the IoT environment is often sensitive, and hence, the need to address the privacy concerns of the data owners. Existing approaches incur a huge computation cost and there is also a gap between privacy preservation and data utility. In this work, a genetic algorithm is coupled with a deep learning network based on adversarial training to build a utility-privacy balanced, low computation solution. The proposal aims to prevent inference of implicit privacy labels present in the data while maintaining data utility. The first part of the proposed work leverages an optimized encoder architecture to learn latent space representation of the input and the second part is the incorporation of adversary for training the framework to prevent unintended sensitive inference. Both parts are governed by a genetic algorithm to output a fitting encoder. Numerical results carried on a benchmark dataset exhibit the capability to protect sensitive data by keeping the accuracy level of the adversary within 23%, and producing a maximum inference accuracy of 95% for the intended task.