Malware Detection and Classification Using Portable Executable File Leveraging Transfer Learning

Abstract

Due to.exponential growth in.malware attacks, industry and governments are heavily affected. Malware analysis and detection has become the hot topic for research. Malware. refers to any software that behaves in a manner that is potentially harmful or malicious, including .viruses, .worms, .spayware, .adware, .trojans, and other similar threats. The detection and analysis of malware typically involves the use of static and dynamic strategies, but these methods can be both .time-consuming and inefficient when it comes to identifying threats in real-time. Advanced strategies like machine learning, deep learning, and transfer learning are used to determine whether any executable file is malware that gives better accuracy and performance. All these strategies use Portable Executable (PE) file header for malware analysis and detection. Transfer learning can help models to generalize better to new and unseen malware samples by leveraging the knowledge learned from related tasks. This can help to improve the robustness and reliability of the model.