Intrusion Detection System Using Improved Gloden Jackal optimization for Security and Privacy in Internet of Things

Technology plays a primary role in rapid growth of service and identifying the quality of life. Recent technology such as Internet of Things (IoT) determines an impressive performance in the development of fast-forward. Intrusion Detection System (IDS) is employed as a lifeline to prevent attacks by categorizing activities as suspicious or normal. However, identifying the most relevant features from large data is challenging to effectively distinguish among suspicious or normal behavior. This research proposes the Improved Gloden Jackal optimization (IGJO) to select the appropriate features in IDS for security and privacy. GJO is improved by using tent mapping reverse learning for initializing populations, sine and cosine techniques are performed for updating prey positions which increases the ability of global exploration, and Cauchy mutation is used to acquire the optimal solutions. Initially, the CIC-IDS2017 dataset is used to evaluate the model performance and min-max normalization is utilized for normalizing the data. Then, IGJO is performed to select the appropriate features and Long Short-Term Memory (LSTM) is employed to classify IDS. The IGJO achieves a high accuracy of 99.95% compared to existing techniques respectively.