Mathematical and Deep Learning-Based Approaches for Advanced Cybersecurity

Dear Colleagues,

This Special Issue aims to showcase new advances and diverse approaches in deep learning techniques for intrusion detection systems, highlighting innovative and practical solutions that address the evolving landscape of cyber threats. We particularly welcome research that demonstrates the deployment impact or real-world applications, emphasising the translation of theoretical advances into practical cybersecurity strategies.

We invite submissions that explore theoretical foundations, mathematical modelling, computational techniques, and practical implementations supporting intrusion detection in the cybersecurity domain. Topics of interest include, but are not limited to, neural network architectures for anomaly detection, optimisation methods for training IDS models, statistical and probabilistic frameworks for network data analysis, and hybrid models integrating deep learning with traditional security algorithms.

We welcome papers addressing issues such as system deployment, interdisciplinary perspectives, and case studies from varied sectors and organisational contexts. Submissions that consider model explainability, performance evaluation, the mathematical validation of system robustness, and practical challenges in implementation are particularly encouraged.

The goal is to foster collaboration among mathematicians, computer scientists, engineers, practitioners, and security researchers to advance intelligent, deployable cyber defence techniques. Submissions may cover, but are not limited to, the following:

• Applications of convolutional and recurrent neural networks for anomaly and threat detection.
• Hybrid or ensemble approaches that combine deep learning methods or integrate with existing security systems.
• Benchmarking deep learning against traditional intrusion detection tools.
• Methods to address issues such as model interpretability, computational efficiency, scalability, and real-world implementation.
• Large-scale network or malware data analysis using AI.
• Tools and frameworks for automated threat response and monitoring.
• Mathematical modelling and theoretical analysis of deep learning techniques for intrusion detection.
• Optimisation methods and convergence analysis in training deep neural networks for security tasks.
• Development of hybrid or ensemble IDS models combining statistical, graph-based, and deep learning approaches.
• Probabilistic and stochastic modelling for network traffic and cyber threat prediction.
• Use of graph neural networks and topological data analysis for cyber threat correlation and pattern discovery.
• Explainable and interpretable deep learning models for transparent cyber defence systems.
• Real-time intrusion detection frameworks deployable on edge or distributed computing environments.
• Mathematical approaches for benchmarking, evaluation metrics, and uncertainty quantification in IDS performance.
• Case studies exploring deployment, challenges, or societal, organisational, and policy-level impact.

Researchers and professionals working at the intersection of artificial intelligence, cybersecurity, and related disciplines are encouraged to submit contributions. Selected papers will offer new insights into detection accuracy, resilience, and practical improvements for real-world systems using deep learning.

Dr. Akanksha Saini
Dr. Abebe Diro
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 250 words) can be sent to the Editorial Office for assessment.

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.

• deep learning
• intrusion detection
• cyber security
• neural networks
• anomaly detection
• network monitoring
• malware
• artificial intelligence
• threat detection
• data analysis
• deployment
• implementation
• real-world impact
• interdisciplinary