Machine Learning for Cybersecurity: Methods and Applications

Dear Colleagues,

Machine learning (ML) and artificial intelligence (AI) are increasingly transforming cybersecurity by enabling the analysis of large volumes of heterogeneous data and supporting the detection, characterization, and mitigation of increasingly sophisticated cyber threats. However, the deployment of ML-based cybersecurity solutions in real-world environments still faces significant challenges, including data quality and representativeness, encrypted communications, evolving attacker behavior, model explainability and robustness, privacy constraints, and the need for efficient and timely detection and response.

This Special Issue, ‘Machine Learning for Cybersecurity: Methods and Applications’, aims to bring together novel methodological advances and practical applications of machine learning, deep learning, and artificial intelligence specifically tailored to cybersecurity challenges. Particular attention will be given to approaches capable of exploiting the complex, heterogeneous, and relational nature of cybersecurity data, including graph-based learning, graph neural networks, knowledge graphs, ontologies, and hybrid data-driven and knowledge-driven approaches. We particularly welcome contributions that go beyond conventional benchmark-based evaluations and investigate the applicability, robustness, interpretability, and operational effectiveness of learning-based security mechanisms in realistic engineering and operational environments.

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

• Machine learning and deep learning for intrusion and anomaly detection;
• Network traffic analysis, classification, and behavioral characterization;
• Security and privacy analysis of encrypted network traffic;
• ML-based detection and characterization of cyberattacks, advanced persistent threats, and insider threats;
• Explainable and interpretable AI for cybersecurity;
• Adversarial machine learning and robustness of ML-based security systems;
• Cyber threat intelligence, attack characterization, and ML-assisted security decision-making;
• Machine learning for dynamic risk assessment and cyber situational awareness;
• Security analytics based on temporal, graph-based, and heterogeneous data;
• Large language models and generative AI for cybersecurity applications;
• Generation, augmentation, quality assessment, and benchmarking of cybersecurity datasets;
• Online learning, concept drift, and adaptation to evolving threats;
• Privacy-preserving and federated machine learning for cybersecurity;
• ML-based security in IoT, mobile, edge, cloud, and distributed environments;
• Integration of ML-based detection with threat modeling and frameworks such as MITRE ATT&CK;
• Ontologies, knowledge graphs, and semantic technologies combined with machine learning for cybersecurity;
• Graph neural networks and graph-based machine learning for cybersecurity applications;
• Knowledge-driven machine learning for cyber threat intelligence, attack modeling, vulnerability analysis, and security decision support;
• Real-time, scalable, and resource-efficient ML-based cybersecurity solutions;
• Experimental methodologies, datasets, testbeds, and reproducible evaluation of AI-enabled cybersecurity systems.

The Special Issue welcomes original research articles, methodological contributions, experimental studies, datasets and benchmarking studies, as well as high-quality reviews addressing emerging challenges at the intersection of machine learning, artificial intelligence, network security, and cybersecurity.

Prof. Dr. Jorge E. López de Vergara
Dr. Xavier A. Larriva-Novo
Dr. Marta Moure Garrido
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-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences 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.