New Advances in Robust Deep-Learning-Based Intrusion Detection and Blockchain Security for IoT

Dear Colleagues,

Deep learning has become one of the most rapidly growing fields and constantly provides many new and advanced models for intrusion detection in the context of the Internet of Things (IoT), especially with regard to defending large-scale IoT devices against various kinds of network attacks. Deep learning models require high-quality datasets for high accuracy classification. However, many IoT intrusion detection datasets consist of discrete numbers and potentially contain more noise than image-based datasets. Thus, the development of advanced data quality enhancement mechanisms is desirable for robust intrusion detection models. In addition, such robust detection models require adversarial attack defenses. Moreover, due to the distributed design of IoT environments, a blockchain is suitable for the distributed security protection of IoT together with deep-learning-based intrusion detection for IoT security.

This Special Issue invites research or review papers on new, advanced, and robust deep-learning-based intrusion detection and blockchain security protection systems for IoT environments. Robust deep-learning-based intrusion detection may involve data quality enhancement and feature selection or extraction. As self-supervised learning and contrastive learning have successfully improved the classification quality of image-based datasets, they offer great potential for improving intrusion detection accuracy. Regarding the detection of adversarial attacks, generative adversarial networks have also become attractive detection solutions for images, so they may be suitable for application to the numeric datasets of intrusion detection. In IoT-distributed environments, the design of blockchain is suitable as a secure distributed ledger offering non-reputable and secure transfer characteristics. Distributed deep learning models such as federated learning can be effectively employed alongside blockchain as a hybrid security defense for IoT-distributed environments.

Examples of some topics of interest are as follows:

• Deep learning
• Intrusion detection
• Data quality enhancement
• Feature selection or extraction
• Self-supervised learning
• Contrastive learning
• Adversarial attack detection
• Generative adversarial networks
• Blockchain
• Federated learning

Dr. Chinyang Henry Tseng
Prof. Dr. Woei-Jiunn Tsaur
Prof. Dr. Hsing-Chung Chen
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. Mathematics is an international peer-reviewed open access semimonthly 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 2600 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.