Please use this identifier to cite or link to this item:
Title: Toward secure and efficient deep learning inference in dependable IoT systems
Authors: Qiu, Han
Zheng, Qinkai
Zhang, Tianwei
Qiu, Meikang
Memmi, Gerard
Lu, Jialiang
Keywords: Engineering::Computer science and engineering
Issue Date: 2021
Source: Qiu, H., Zheng, Q., Zhang, T., Qiu, M., Memmi, G. & Lu, J. (2021). Toward secure and efficient deep learning inference in dependable IoT systems. IEEE Internet of Things Journal, 8(5), 3180-3188.
Project: CHFA-GC1-AW03
Journal: IEEE Internet of Things Journal
Abstract: The rapid development of deep learning (DL) enables resource-constrained systems and devices [e.g., Internet of Things (IoT)] to perform sophisticated artificial intelligence (AI) applications. However, AI models, such as deep neural networks (DNNs), are known to be vulnerable to adversarial examples (AEs). Past works on defending against AEs require heavy computations in the model training or inference processes, making them impractical to be applied in IoT systems. In this article, we propose a novel method, Super-IoT, to enhance the security and efficiency of AI applications in distributed IoT systems. Specifically, Super-IoT utilizes a pixel drop operation to eliminate adversarial perturbations from the input and reduce network transmission throughput. Then, it adopts a sparse signal recovery method to reconstruct the dropped pixels and wavelet-based denoising method to reduce the artificial noise. Super-IoT is a lightweight method with negligible computation cost to IoT devices and little impact on the DNN model performance. Extensive evaluations show that it can outperform three existing AE defensive solutions against most of the AE attacks with better transmission efficiency.
ISSN: 2327-4662
DOI: 10.1109/JIOT.2020.3004498
Rights: © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at:
Fulltext Permission: open
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Journal Articles

Files in This Item:
File Description SizeFormat 
paper.pdf1.49 MBAdobe PDFView/Open

Citations 20

Updated on May 17, 2022

Citations 20

Updated on May 11, 2022

Page view(s)

Updated on Jul 3, 2022

Download(s) 50

Updated on May 17, 2022

Google ScholarTM




Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.