Enhancing Network Security: A Comparative Analysis of Deep Learning and Machine Learning Models for Intrusion Detection
Arunima Ajeesh, Tessy Mathew · 2024
The escalating reliance of computer networks on security systems exposes them to increasing threats. In response, an advanced security system is proposed, utilizing machine learning and deep learning techniques and leveraging the NSLKDD and CSE-CIC-IDS2018 datasets. Addressing the class imbalance challenges, the DSSTE algorithm is adopted to optimize model performance. Evaluation involves six, machine learning and deep learning methods: XGBoost, LSTM, Bi-LSTM, CNN, and VGG19, with a focus on assessing speed, false positive rate and detection efficiency. Experimental results underscore DSSTE's efficacy in mitigating class imbalance and enhancing overall intrusion detection. The proposed IDS, empowered by machine learning and DSSTE, ensures early detection and strengthens network security by countering intrusion attempts. Performance is compared with systems utilizing SMOTE and ADAASYN for data balancing.