Securing Big Data Analytics for Cyber-Physical Systems

A special issue of Future Internet (ISSN 1999-5903). This special issue belongs to the section "Cybersecurity".

Deadline for manuscript submissions: closed (20 October 2023) | Viewed by 8114

Special Issue Editors

Department of Computer & Information Sciences, Towson University, Towson, MD 21252, USA
Interests: cyber security and privacy; cyber-physical systems/Internet of Things; data and machine learning-driven applications
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Department of Computer & Information Sciences, Towson University, Towson, MD 21252, USA
Interests: big data analytics; cybersecurity, and networking in cyber physical systems and IoT
Special Issues, Collections and Topics in MDPI journals
Department of Computer Science, Sam Houston State University, Huntsville, TX 77341, USA
Interests: effective and secure deep learning-driven data analytics in internet of things systems; distributed computing in IoT; data analysis

Special Issue Information

Dear Colleagues,

Recent advances in edge computing, artificial intelligence, and big data technologies have given rise to cyber-physical systems (CPS)/Internet of Things (IoT), which are emerging paradigms to meet the demands of flexibility, agility, and ubiquitous accessibility of cyberspace. The proliferation of smart devices and applications in our everyday lives have generated increasingly tremendous data. With the help of central/edge servers or other devices, smart nodes are now capable of extracting insightful analytics from collected data, providing unprecedented opportunities of data-driven economy that finds applications in diverse sectors ranging from smart health and smart transportation to predictive maintenance and smart manufacturing, etc. Despite this ongoing advancement in CPS/IoT, there are growing concerns regarding the security and privacy of data owners when they grant smart applications direct access to sensors and their data. Particularly, CPS/IoT devices are vulnerable to different kinds of attacks such as Mirai Botnet, webcam hack, DDoS attacks, etc. The intrinsic heterogeneity of data, application, hardware, and software in CPS/IoT systems further expands the attack surface and escalates the challenges of deploying universal security strategies. Furthermore, IoT-based systems that handle both security and privacy-sensitive data (i.e., data in healthcare, energy, transportation critical infrastructure systems) need to promptly react to adversarial activities and prevent the disclosure of privacy-sensitive data. Therefore, how to secure data-driven analytics is an important issue in CPS/IoT systems. This special issue aims at the state-of-the-art research efforts on secure data-driven analytics for CPS/IoT. The topics of interest include, but are not limited to:

  • Reliability, consistency, robustness and security of AI in CPS/IoT
  • IoT data analytics for anomaly detection
  • Security management of IoT devices based on data knowledge
  • Adversarial example attacks and defense in IoT Systems
  • Threat modelling and risk assessment in IoT
  • Security of blockchain and decentralized schemes for IoT
  • Deep learning-based security solutions for intelligent CPS and IoT
  • Secure and privacy-preserving CPS and IoT architectures
  • Security analysis and enhancement in edge and IoT
  • Privacy protection in edge computing assisted with evolving IoT
  • Evaluation platforms and hardware-in-the-loop testbeds for AI-enabled IoT environments
  • Foundation and application of data science in CPS/IoT systems

Prof. Dr. Wei Yu
Dr. Weixian Liao
Dr. Fan Liang
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Future Internet is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Cyber-physical systems (CPS)
  • Internet of Things (IoT)
  • security and vulnerability analysis
  • big data analytics

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

15 pages, 4892 KiB  
Article
Knowledge Distillation-Based GPS Spoofing Detection for Small UAV
by Yingying Ren, Ryan D. Restivo, Wenkai Tan, Jian Wang, Yongxin Liu, Bin Jiang, Huihui Wang and Houbing Song
Future Internet 2023, 15(12), 389; https://doi.org/10.3390/fi15120389 - 30 Nov 2023
Viewed by 1287
Abstract
As a core component of small unmanned aerial vehicles (UAVs), GPS is playing a critical role in providing localization for UAV navigation. UAVs are an important factor in the large-scale deployment of the Internet of Things (IoT) and cyber–physical systems (CPS). However, GPS [...] Read more.
As a core component of small unmanned aerial vehicles (UAVs), GPS is playing a critical role in providing localization for UAV navigation. UAVs are an important factor in the large-scale deployment of the Internet of Things (IoT) and cyber–physical systems (CPS). However, GPS is vulnerable to spoofing attacks that can mislead a UAV to fly into a sensitive area and threaten public safety and private security. The conventional spoofing detection methods need too much overhead, which stops efficient detection from working in a computation-constrained UAV and provides an efficient response to attacks. In this paper, we propose a novel approach to obtain a lightweight detection model in the UAV system so that GPS spoofing attacks can be detected from a long distance. With long-short term memory (LSTM), we propose a lightweight detection model on the ground control stations, and then we distill it into a compact size that is able to run in the control system of the UAV with knowledge distillation. The experimental results show that our lightweight detection algorithm runs in UAV systems reliably and can achieve good performance in GPS spoofing detection. Full article
(This article belongs to the Special Issue Securing Big Data Analytics for Cyber-Physical Systems)
Show Figures

Figure 1

28 pages, 889 KiB  
Article
Survey of Distributed and Decentralized IoT Securities: Approaches Using Deep Learning and Blockchain Technology
by Ayodeji Falayi, Qianlong Wang, Weixian Liao and Wei Yu
Future Internet 2023, 15(5), 178; https://doi.org/10.3390/fi15050178 - 11 May 2023
Cited by 4 | Viewed by 2627
Abstract
The Internet of Things (IoT) continues to attract attention in the context of computational resource growth. Various disciplines and fields have begun to employ IoT integration technologies in order to enable smart applications. The main difficulty in supporting industrial development in this scenario [...] Read more.
The Internet of Things (IoT) continues to attract attention in the context of computational resource growth. Various disciplines and fields have begun to employ IoT integration technologies in order to enable smart applications. The main difficulty in supporting industrial development in this scenario involves potential risk or malicious activities occurring in the network. However, there are tensions that are difficult to overcome at this stage in the development of IoT technology. In this situation, the future of security architecture development will involve enabling automatic and smart protection systems. Due to the vulnerability of current IoT devices, it is insufficient to ensure system security by implementing only traditional security tools such as encryption and access control. Deep learning and blockchain technology has now become crucial, as it provides distinct and secure approaches to IoT network security. The aim of this survey paper is to elaborate on the application of deep learning and blockchain technology in the IoT to ensure secure utility. We first provide an introduction to the IoT, deep learning, and blockchain technology, as well as a discussion of their respective security features. We then outline the main obstacles and problems of trusted IoT and how blockchain and deep learning may be able to help. Next, we present the future challenges in integrating deep learning and blockchain technology into the IoT. Finally, as a demonstration of the value of blockchain in establishing trust, we provide a comparison between conventional trust management methods and those based on blockchain. Full article
(This article belongs to the Special Issue Securing Big Data Analytics for Cyber-Physical Systems)
Show Figures

Figure 1

13 pages, 7114 KiB  
Article
View Synthesis with Scene Recognition for Cross-View Image Localization
by Uddom Lee, Peng Jiang, Hongyi Wu and Chunsheng Xin
Future Internet 2023, 15(4), 126; https://doi.org/10.3390/fi15040126 - 28 Mar 2023
Cited by 1 | Viewed by 1493
Abstract
Image-based localization has been widely used for autonomous vehicles, robotics, augmented reality, etc., and this is carried out by matching a query image taken from a cell phone or vehicle dashcam to a large scale of geo-tagged reference images, such as satellite/aerial images [...] Read more.
Image-based localization has been widely used for autonomous vehicles, robotics, augmented reality, etc., and this is carried out by matching a query image taken from a cell phone or vehicle dashcam to a large scale of geo-tagged reference images, such as satellite/aerial images or Google Street Views. However, the problem remains challenging due to the inconsistency between the query images and the large-scale reference datasets regarding various light and weather conditions. To tackle this issue, this work proposes a novel view synthesis framework equipped with deep generative models, which can merge the unique features from the outdated reference dataset with features from the images containing seasonal changes. Our design features a unique scheme to ensure that the synthesized images contain the important features from both reference and patch images, covering seasonable features and minimizing the gap for the image-based localization tasks. The performance evaluation shows that the proposed framework can synthesize the views in various weather and lighting conditions. Full article
(This article belongs to the Special Issue Securing Big Data Analytics for Cyber-Physical Systems)
Show Figures

Figure 1

17 pages, 2482 KiB  
Article
Privacy-Preserving Object Detection with Secure Convolutional Neural Networks for Vehicular Edge Computing
by Tianyu Bai, Song Fu and Qing Yang
Future Internet 2022, 14(11), 316; https://doi.org/10.3390/fi14110316 - 31 Oct 2022
Cited by 4 | Viewed by 1719
Abstract
With the wider adoption of edge computing services, intelligent edge devices, and high-speed V2X communication, compute-intensive tasks for autonomous vehicles, such as object detection using camera, LiDAR, and/or radar data, can be partially offloaded to road-side edge servers. However, data privacy becomes a [...] Read more.
With the wider adoption of edge computing services, intelligent edge devices, and high-speed V2X communication, compute-intensive tasks for autonomous vehicles, such as object detection using camera, LiDAR, and/or radar data, can be partially offloaded to road-side edge servers. However, data privacy becomes a major concern for vehicular edge computing, as sensitive sensor data from vehicles can be observed and used by edge servers. We aim to address the privacy problem by protecting both vehicles’ sensor data and the detection results. In this paper, we present vehicle–edge cooperative deep-learning networks with privacy protection for object-detection tasks, named vePOD for short. In vePOD, we leverage the additive secret sharing theory to develop secure functions for every layer in an object-detection convolutional neural network (CNN). A vehicle’s sensor data is split and encrypted into multiple secret shares, each of which is processed on an edge server by going through the secure layers of a detection network. The detection results can only be obtained by combining the partial results from the participating edge servers. We have developed proof-of-concept detection networks with secure layers: vePOD Faster R-CNN (two-stage detection) and vePOD YOLO (single-stage detection). Experimental results on public datasets show that vePOD does not degrade the accuracy of object detection and, most importantly, it protects data privacy for vehicles. The execution of a vePOD object-detection network with secure layers is orders of magnitude faster than the existing approaches for data privacy. To the best of our knowledge, this is the first work that targets privacy protection in object-detection tasks with vehicle–edge cooperative computing. Full article
(This article belongs to the Special Issue Securing Big Data Analytics for Cyber-Physical Systems)
Show Figures

Figure 1

Back to TopTop