Guest Editors
Dr. Jevier Bermejo Higuera
Email: javier.bermejo@unir.net
Affiliation: Faculty of Engineering, Universidad International de La Rioja, Av. de la Paz, 137, 26006 Logroño, Spain
Homepage:
Research Interests: malware analysis, software security, cryptography
Dr. Juan Ramón Bermejo Higuera
Email: juanramon.bermejo@unir.net
Affiliation: School of Engineering and Technology, International University of La Rioja, Avda. de La Paz, 137, Logroño, 26006, La Rioja, Spain
Homepage:
Research Interests: software security, web security, malware analysis
Summary
Malware detection is one of the fundamental pillars of contemporary cybersecurity. In a digital ecosystem characterized by global interconnection, malware represents one of the most dangerous and constantly evolving threats.
Historically, detection techniques relied primarily on static signatures, which allowed known malware families to be identified using predefined patterns. However, the proliferation of polymorphic variants, the use of packers, code obfuscation, and, more recently, the use of artificial intelligence by attackers have reduced the effectiveness of these conventional approaches.
Over the last decade, the most significant advances in malware detection have focused on the application of machine learning and deep learning techniques, which are capable of identifying patterns of malicious activity without relying exclusively on static signatures. Likewise, the development of more realistic sandboxing environments, the adoption of collaborative rules such as YARA and Sigma, and the integration of threat intelligence platforms have significantly strengthened early detection and response capabilities.
In this context, the study of malware detection has not only technical value, but also strategic and social value. The following subtopics are the particular interests of this special issue, including but not limited to:
· Development of ML/DL models for malware detection
· Manipulation of malware samples to evade detection models
· Malware detection in IoT/IoMT/IoUAV environments
· Combination of multiple types of features and ensemble learning.
· Early detection of emerging malware ("zero-day," "first-time-appeared malware")
· Innovative feature representations for malware classification
· Network and network traffic-based analysis and detection, including C2, exfiltration, malware persistence
Keywords
Malware detection, Cybersecurity, Machine learning, Threat intelligence,Behavioral analysis, Static analysis, Dynamic analysis, Polymorphism, Obfuscation, Sandboxing
Login
Register
Submit a Paper
Propose a Special lssue