Malware Classification

Malware classification aims to automatically categorize malicious software, enabling faster and more efficient detection and response to cyber threats. Current research focuses on improving classification accuracy and efficiency using various deep learning architectures, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), vision transformers, and graph neural networks (GNNs), often incorporating techniques like transfer learning, multi-task learning, and semi-supervised learning to handle limited labeled data. These advancements are crucial for enhancing cybersecurity defenses, enabling quicker identification of new malware variants, and improving the understanding of malware behavior through explainable AI (XAI) methods. The field also actively addresses challenges like adversarial attacks, data bias, and the need for robust and reproducible research methodologies.

Papers