"MalVol-25: A Diverse, Labeled and Detailed Malware Volatile Memory Dataset for Detection and Response Testing and Validation"
Year: 2025
Type: preprint
Abstract: "This paper addresses the critical need for high-quality malware datasets that support advanced analysis techniques, particularly reinforcement learning (RL). Existing datasets often lack diversity, comprehensive labelling, and the complexity necessary for effective RL training. To fill this gap, we developed a systematic dataset generation approach combining automated malware execution in controlled virtual environments with dynamic monitoring tools. The resulting dataset comprises clean and infected memory snapshots across multiple malware families and operating systems, capturing detailed behavioural and environmental features. Key design decisions include applying ethical and legal compliance, thorough validation using both automated and manual methods, and comprehensive documentation to ensure replicability and integrity. The dataset\u2019s distinctive features enable modelling system states and transitions, facilitating RL-based malware detection and response strategies. This resource is significant for advancing adaptive cybersecurity defences and digital forensic research. Its scope supports diverse malware scenarios and offers potential for broader applications in incident response and automated threat mitigation."
Source: arXiv (Cornell University)
DOI: 10.21227/kg5b-nf37
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W4415345558