Leveraging Dual-Generative Adversarial Networks for Adversarial Malware Detection via Ensemble Learning

Abstract


 
 
 
 In the expanding realm of cybersecurity, machine learning-based malware detection has emerged as a vital line of defense. However, the growing sophistication of malware attacks poses formidable challenges to conventional detection systems. To address this, this paper uses a Generative Adversarial Network that utilizes dual generators for adversarial learning on malware, designed to enhance the detection of harmful Portable Executable (PE) files. Our model employs a two-tiered generator system within the GAN architecture, where the secondary generator intervenes when the primary generator yields a malware PE executable dismissed by the detector.
 The detection unit leverages ensemble learning techniques to analyze the PE software feature vector, capitalizing on the synergy of multiple learning models for improved performance and generalization. This setup empowers the system to generate a broader range of adversarial examples and respond to them effectively, enhancing the robustness of the detector against previously unseen or variable malware types.