AESMOTE: Adversarial Reinforcement Learning with SMOTE for Anomaly Detection

Intrusion Detection Systems (IDSs) play a vital role in securing today's Data-Centric Networks. In a dynamic environment that is vulnerable to various types of attacks, novel, fast, and robust solutions are in demand to handle fast changing threats and thus the ever-increasing difficulty of detection . In this dissertation, we present a novel reinforcement learning based anomaly detection algorithm that further enables anomaly-based intrusion detection. Our proposed solution is developed based on AE-RL. An adapted SMOTE is introduced to address the data imbalance problem while remodel the behaviors of the environmental agent for better performance. Using techniques such as SMOTE, ROS, NearMiss1 and NearMiss2, performance measures obtained from our simulations have led us to recognize specific performance trends. The proposed model AESMOTE outperforms the original AE-RL in several cases. Experiment results show an Accuracy greater than 0.82 and F1 greater than 0.824.