Genetic algorithm and artificial neural network for network forensic analytics

Rapid development of Internet of things (IoT) technologies and their application and importance within various fields arises security issues. New threats require development of appropriate approaches to address them since information security problems could led to serious damages. This work focuses on developing methods for prediction of undesired behavior. Literature review indicated use of advanced statistical approaches such as logistic regression or multiple regression. However, in the recent years, interest among researchers for applying artificial intelligence techniques is growing. Artificial intelligence approaches shown to be powerful tool for development of efficient predictive models in various fields. Main aim of research presented here is to apply artificial intelligent techniques for intrusion analysis. Our approach is based on the neural networks and genetic algorithms. Neural networks results largely depend on the network parameters which are mostly achieved by trial-and-error. Trial-and-error approach requires a lot of time. Thus, we are applying genetic algorithm to optimize neural networks parameters. Experiments are conducted on the publicly available new dataset, Bot-IoT, consisting of legitimate and simulated IoT network traffic incorporating different types of attacks. Here, we investigate: (i) the level to which available data can be a good basis for predicting intrusion, (ii) efficiency of neural network approach supported by genetic algorithm for developing useful predictive models.