Please use this identifier to cite or link to this item:
|Title:||Privacy and security issues in deep learning : a survey||Authors:||Liu, Ximeng
Vasilakos, Athanasios V.
|Keywords:||Engineering::Electrical and electronic engineering||Issue Date:||2020||Source:||Liu, X., Xie, L., Wang, Y., Zou, J., Xiong, J., Ying, Z., & Vasilakos, A. V. (2021). Privacy and security issues in deep learning : a survey. IEEE Access, 9, 4566-4593. doi:10.1109/ACCESS.2020.3045078||Journal:||IEEE Access||Abstract:||Deep Learning (DL) algorithms based on artificial neural networks have achieved remarkable success and are being extensively applied in a variety of application domains, ranging from image classification, automatic driving, natural language processing to medical diagnosis, credit risk assessment, intrusion detection. However, the privacy and security issues of DL have been revealed that the DL model can be stolen or reverse engineered, sensitive training data can be inferred, even a recognizable face image of the victim can be recovered. Besides, the recent works have found that the DL model is vulnerable to adversarial examples perturbed by imperceptible noised, which can lead the DL model to predict wrongly with high confidence. In this paper, we first briefly introduces the four types of attacks and privacy-preserving techniques in DL. We then review and summarize the attack and defense methods associated with DL privacy and security in recent years. To demonstrate that security threats really exist in the real world, we also reviewed the adversarial attacks under the physical condition. Finally, we discuss current challenges and open problems regarding privacy and security issues in DL.||URI:||https://hdl.handle.net/10356/145999||ISSN:||2169-3536||DOI:||10.1109/ACCESS.2020.3045078||Rights:||© 2020 IEEE. This journal is 100% open access, which means that all content is freely available without charge to users or their institutions. All articles accepted after 12 June 2019 are published under a CC BY 4.0 license, and the author retains copyright. Users are allowed to read, download, copy, distribute, print, search, or link to the full texts of the articles, or use them for any other lawful purpose, as long as proper attribution is given.||Fulltext Permission:||open||Fulltext Availability:||With Fulltext|
|Appears in Collections:||EEE Journal Articles|
Updated on Dec 3, 2022
Web of ScienceTM
Updated on Nov 29, 2022
Updated on Dec 6, 2022
Updated on Dec 6, 2022
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.