Machine Learning for Cyber-Physical Security

Dear Colleagues,

Powered by advanced communication and computation technologies, our world is steadily transforming into an inter-connected cyber-physical system, which manifests itself in many domains including smart power grids, smart transportation systems, autonomous vehicles, industrial automation, health monitoring, etc. Such progress results in two implications. On one hand, this advancement has dramatically increased the attack surface and introduced new damaging types of cyber-attacks. On the other hand, data-driven techniques have been popular in detecting such cyber-attacks because of the vast streams of data available from the cyber-physical systems.

The adoption of machine learning techniques in cyber-security is highly motivated by the recent advancement in computational power and processing speed. However, this adoption is challenged by several issues. The first challenge is the limited access to benchmark datasets needed to develop and compare data-driven solutions. Furthermore, unified security measures need to be introduced to assess and compare various data-driven solutions. In addition, more attention should be given to developing privacy-preserving machine-learning models. Moreover, further investigations are required on the adoption of machine learning techniques to introduce novel attack and threat models.

This Special Issue aims to promote research in developing new machine-learning models for the security and privacy of cyber-physical systems and introducing new threat and attack models based on machine-learning techniques. Submissions can include original research, dataset collection and benchmarking, or surveys and tutorials. The research topics to be covered in this Special Issue include but are not limited to: 

• Deep machine learning for security and privacy;
• Privacy-preserving machine learning;
• Adversarial machine learning in cyber security;
• Reinforcement learning for security and privacy;
• Data-driven access control;
• Authentication using machine learning;
• Cryptographic analysis with machine learning;
• Malware, intrusion, spam, and phishing detection using machine learning ;
• Threat and attack model generation using machine learning;
• Penetration testing using machine learning;

Dr. Muhammad Ismail
Guest Editor

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. Information 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.

• deep machine learning
• reinforcement learning
• generative adversarial networks
• privacy and security