The Effectiveness of Zero-Day Attacks Data Samples Generated via GANs on Deep Learning Classifiers

Digitization of most of the services that people use in their everyday life has, among others, led to increased needs for cybersecurity. As digital tools increase day by day and new software and hardware launch out-of-the box, detection of known existing vulnerabilities, or zero-day as they are commonly known, becomes one of the most challenging situations for cybersecurity experts. Zero-day vulnerabilities, which can be found in almost every new launched software and/or hardware, can be exploited instantly by malicious actors with different motives, posing threats for end-users. In this context, this study proposes and describes a holistic methodology starting from the generation of zero-day-type, yet realistic, data in tabular format and concluding to the evaluation of a Neural Network zero-day attacks’ detector which is trained with and without synthetic data. This methodology involves the design and employment of Generative Adversarial Networks (GANs) for synthetically generating a new and larger dataset of zero-day attacks data. The newly generated, by the Zero-Day GAN (ZDGAN), dataset is then used to train and evaluate a Neural Network classifier for zero-day attacks. The results show that the generation of zero-day attacks data in tabular format reaches an equilibrium after about 5000 iterations and produces data that are almost identical to the original data samples. Last but not least, it should be mentioned that the Neural Network model that was trained with the dataset containing the ZDGAN generated samples outperformed the same model when the later was trained with only the original dataset and achieved results of high validation accuracy and minimal validation loss.