Generative Adversarial Networks in Anomaly Detection and Malware Detection: A Comprehensive Survey

The swiftly changing panorama of machine learning has observed first-rate leaps within the field of Generative Adversarial Networks (GANs). In the beginning, the implantation of a deep neural network seemed quite difficult and poses challenges. However, with the rapid development of huge processing power, different machine learning models such as Convolutional Neural Networks, Recurrent Neural Networks, and GANs have emerged in the past few years. Following Ian Goodfellow’s proposed GANs model in 2014, there has been a huge increase in the research focused on Generative Adversarial Networks. In the present context, not only GANs are used in feature extraction, but it proves itself worthy in the domain of anomaly and malware detection having firmly established in this field. Therefore, in our research paper, we conducted a comprehensive survey of prior and current research attempts in anomaly and malware detection using GANs. This research paper aims to provides detailed insights to the reader about what types of GANs are used for anomaly and malware detection with a general overview of the different types of GANs. These results are provided by analyzing both past and present GAN surveys performed, along with detailed information regarding the datasets used in these surveyed papers. Furthermore, this paper also explores the potential future use of GANs to overcome the advancing threats and malware.