Robust Machine Learning for Cybersecurity

Dear Colleagues,

Machine learning (ML) and Artificial Intelligence (AI) techniques are increasingly adopted in cybersecurity to address complex and large-scale security challenges, including intrusion detection, malware analysis, network traffic classification, fraud detection and threat intelligence. While these data-driven approaches have demonstrated remarkable performance, their deployment in real-world security environments remains challenging due to issues related to robustness, reliability and trustworthiness. Adversarial attacks, data poisoning, evasion strategies, concept drift, noisy or incomplete data and rapidly evolving threat landscapes can significantly degrade the effectiveness of machine learning-based cybersecurity systems.

Robust machine learning has therefore become a critical research direction for cybersecurity applications. It aims to develop models and learning frameworks that maintain stable and reliable performance under adversarial conditions, uncertain environments and distributional shifts. Ensuring robustness is essential for building dependable cybersecurity solutions that can operate safely in dynamic, large-scale and potentially hostile settings such as cloud platforms, Internet of Things (IoT) networks, cyber–physical systems and edge computing infrastructures.

This Special Issue, entitled “Robust Machine Learning for Cybersecurity”, aims to provide a forum for researchers and practitioners to present recent advances, methodologies and applications that enhance the robustness of machine learning models in cybersecurity. The issue seeks high-quality original research articles and review papers that address both theoretical and practical aspects of robustness, including robust model design, adversarial resilience, secure learning mechanisms and rigorous evaluation under realistic attack scenarios.

Topics of interest include, but are not limited to, the following:

1. Adversarial machine learning for cybersecurity;
2. Robust training and evaluation of security-oriented ML models;
3. Defenses against adversarial evasion and data poisoning attacks;
4. Robust malware, ransomware and botnet detection;
5. Intrusion detection and network traffic analysis under adversarial conditions;
6. Concept drift detection and adaptation in security systems;
7. Uncertainty-aware, explainable and interpretable ML for cybersecurity;
8. Privacy-preserving and secure learning techniques (e.g., federated learning, differential privacy, secure aggregation);
9. Robust ML for IoT, edge computing and cyber–physical systems;
10. Benchmarking, datasets and reproducibility for robust cybersecurity ML;
11. Real-world deployments and case studies of robust ML-based security systems.

Prof. Dr. Benjamin Aziz
Dr. Shahadate Rezvy
Dr. Alaa Mohasseb
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. 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.

• robust machine learning
• cybersecurity
• adversarial learning
• intrusion detection
• privacy-preserving learning