Applications of Deep Learning in Cyber Threat Detection

Dear Colleagues,

The exponential growth of network intrusions and cyberattacks poses a significant threat to critical infrastructure across various sectors (including power, autonomous driving, IoT systems, and among others). This growth necessitates the development of advanced artificial intelligence techniques for cyber threat detection where securing current systems and networks against such threats will safeguard computer network systems against malicious activities, initiated by internal users or external infiltrators.

With recent advancements in deep learning over the past decade, this design paradigm has paved the way for the development of AI models that are capable of automatically detecting cyber intrusions. The current trend is developing AI-based systems that have both strong classification accuracy (leveraging various AI algorithms) while providing insights about their behavior and reasoning.

To achieve such a goal, interdisciplinary areas of research are needed (including using single deep learning methods and ensemble techniques for enhancing the accuracy of cyber threat detection, leveraging explainable AI for understanding the decision-making of these deep learning cyber threat detection models, and testing the efficiency and robustness of the developed deep learning-based threat detection methods).

The Special Issue focuses on the discussion of emerging solutions suitable for accomplishing efficient and reliable security technologies that leverage deep learning approaches. Potential topics of interest include, but are not limited to, the following:

• Deep learning methods for advanced network intrusion detection;
• Deep learning-based ensemble learning methods for cyber threat detection;
• Explainable AI for explaining black-box deep learning methods in network intrusion detection;
• Efficiency analysis and optimization of deep learning methods for cyber threat detection;
• Deep learning methods for detecting threats to Internet-of-things (IoT) networks;
• Feature selection for enhancing performance of deep learning methods for cyberthreat detection;
• Evaluation frameworks for current deep learning methods for cyber threat detection;
• Reliability of deep learning-based cyber threat detection methods;
• Adversarial attacks on deep neural networks for cyber threat detection.

We look forward to receiving your contributions. 

Dr. Mustafa Abdallah
Dr. Xiao Luo
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. Electronics 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 2400 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 learning
• network security
• intrusion detection
• explainable AI
• IoT
• deep neural networks
• ensemble learning
• feature selection
• adversarial attacks on DNNs
• cyber security