This is the authors' abstract. We don't add key points for this paper.
This study focuses on applying Natural Language Processing (NLP) in Windows malware detection to address the complex problem of classifying and detecting diverse malware patterns. The proposed method combines both static and dynamic malware attributes, using NLP to analyze and understand linguistic characteristics within the malware. By using readable strings and API sequences from analyzed results as inputs to a deep learning multimodal, our proposed method can achieve a high accuracy of 0.99 for the classification task and 0.96 accuracy for the time-based detection task. The combination of static features like strings and dynamic attributes such as API sequences, along with the use of NLP, provides a comprehensive and effective approach to detecting malware in a practical environment.
Answers are grounded in this paper and cite their sources.
No takes yet. Share an insight, caveat, or question.
Hien et al. (2024) studied this question.
Synapse has enriched 8 closely related papers on similar clinical questions. Consider them for comparative context: