Call for Papers

The proliferation of Cyber-Physical Systems (CPSs), including Internet of Things (IoT), is changing our lives. The benefits of low-power wireless communication technology in CPSs are widely acknowledged, ranging from better scalability through lower installation and maintenance costs to greater flexibility in selecting sensing and actuation points. Example applications include level control of dangerous liquids, rapid prototyping of automation solutions in retrofitting buildings, and minimally invasive monitoring of safety-critical assets. One of the open issues that may slow down the development of CPSs is related to security. CPSs applications are often associated with sensitive data, core infrastructures and assets, making them attractive in terms of vulnerability, data breach, and denial of services. Moreover, the heterogeneity in terms of protocols, operating systems, and devices combined with poor adoption of standard solutions create insecure design, architectures and deployments. In addition, due to the use of wireless technologies, secure communication is strongly needed to protect valuable information. Therefore, secure communication management has become a crucial aspect in developing trustworthy systems with the preservation of security and privacy for next-generation CPSs.

Recently, there has been a surge of efforts to apply machine learning to security, including spoofing attacks, jamming attacks on data transmission, and other attacks that target spectrum sensing and signal classification tasks. However, simple machine learning methods exhibit inherent limitations in translating theory to practice when handling the complexity of optimization for emerging applications with high degrees of freedom. Deep learning (DL) has a strong potential to overcome this challenge via data-driven solutions and improve the performance of CPSs in utilizing limited spectrum resources. DL is a more powerful method of data exploration to learn about ‘normal’ and ‘abnormal’ behavior according to how CPSs components and devices interact with one another. The input data of each part of the CPSs can be collected and investigated to determine normal patterns of interaction, thereby identifying malicious behavior at early stages. Moreover, DL methods could be important in predicting new attacks, which are often mutations of previous attacks, because they can intelligently predict future unknown attacks by learning from existing examples. Consequently, CPSs must have a transition from merely facilitating secure communication among devices to security-based intelligence enabled by DL methods for effective and secure systems.

However, the challenge in applying DL for secure communication in CPSs is yet to be addressed. Such challenges include but are not limited to risks and regulatory issues as well as other associated factors related to processing, storage, and availability for secure communication. The goal of this Special Issue is to bring together researchers from different fields to focus on understanding security challenges of CPSs, and architect innovative solutions with the help of cutting-edge DL related technologies. Technical scope of this special issue includes, but is not limited to:

• Theories and algorithms for DL-enabled secure communication in CPSs
• DL driven secure communications in 5G and beyond for CPSs
• Security and privacy issues in DL-based mobile sensing in CPSs
• DL-based decentralized security solutions for CPSs
• DL-based architectures, designs, and applications for smart factory
• DL-based frameworks and software platforms for security in CPSs
• DL for edge and fog computing in CPSs
• Adversarial DL methods for wireless network security
• DL for software-defined networking based CPSs
• DL schemes for decentralized secure transactions in CPSs
• IoT applications based on DL technology in CPSs
• Verification, validation, testing, and analysis for DL solutions in CPSs
• Other emerging solutions for DL driven secure communication in CPSs

Submission Guidelines

Manuscripts should conform to the standard format as indicated in the Information for Authors section of the Paper Submission Guidelines. All manuscripts to be considered for publication must be submitted by the deadline through Manuscript Central. Select “April 2022/Deep Learning Driven Secure Communication for Cyber Physical Systems” from the drop-down menu of Topic/Series titles.

Important Dates

Manuscript Submission Deadline: 15 July 2021
Initial Decision Date: 1 October 2021
Revised Manuscript Due: 1 November 2021
Final Decision Date: 1 December 2021
Final Manuscript Due: 15 February 2022
Publication Date: April 2022

Guest Editors

Wei Wei
Xi’an University of Technology, China

Ching-Hsien Hsu
Asia University, Taiwan

Vincenzo Piuri
Università degli Studi di Milano, Italy

Ammar Rayes
Cisco Systems, USA