Network Intrusion Detection System using 2D Anomaly Detection

Abstract

As connected devices diversified, the attack surfaces and types of network intrusion increased. The conventional intrusion detection methods, such as rule-based methods, cannot detect novel attack types due to their design. For deep learning method research, RNN or LSTM-based anomaly detection exists. However, this method requires high computational power, making it difficult to implement in environments where GPU or TPU cannot be utilized. This paper introduces a 2D anomaly detection method for network intrusion detection. The proposed 2D anomaly detection method requires less computational power than the LSTM or RNN model but performs comparably. Our methods can detect multiple packets at once. Provided methods require less computational power, they can be implemented in an environment with low computational power, i.e. IoT devices. The existing accuracy calculation methods cannot accurately evaluate the proposed methods' multiple packet detection. Therefore, this paper proposes a novel calculation method for multiple anomaly detection. The UNSW-NB15 Dataset was used for training and testing and achieved 99.51%, 97.84%, and 97.88% accuracy on each binary, gray, original method.