• R V Manikanta
• Rajasrinivas Mallu
• Ch. Uma Mahesh
• V Rambabu

Intrusion Detection Systems are very important for computer networks as they protect against attacks that lead to data leaks and privacy breaches. In recent years, researchers have developed machine learning and deep learning techniques to detect anomalies of network in Intrusion Detection Systems (IDS). However, the existing IDS models are efficient in detecting few of the aforementioned attacks. This deficiency makes it difficult to choose an appropriate IDS model when a user does not know what attacks to expect. IDS implements different methods like anomaly based methods and signature based methods for detecting intrusions. Anomaly based methods become popular for detecting new intrusions when compared with signature based methods. Most of the researchers proposed machine learning algorithms for anomaly based detection methods. Some researchers observed that the machine learning algorithms performance was dropped when the dataset contains huge number of records. Further, most of the researchers developed methods based on deep learning techniques for detecting different varieties of intrusions. In this work, we proposed an approach for intrusion detection system by using three different deep learning techniques such as Recurrent Neural Networks, Long Short Term Memory, and Gated Recurrent Unit. The experiment carried out on the dataset of CICIDS 2017 dataset. The deep learning techniques attained best accuracies for intrusion detection when compared with other existing approaches.

Intrusion Detection System, Deep Learning Techniques, RNN, LSTM, GRU, CIcIDS2017 Dataset.

"A Deep Learning Techniques based Approach for Intrusion Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.10, Issue 5, page no.j310-j316, May-2023, Available :http://www.jetir.org/papers/JETIR2305990.pdf

"A Deep Learning Techniques based Approach for Intrusion Detection System", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.10, Issue 5, page no. ppj310-j316, May-2023, Available at : http://www.jetir.org/papers/JETIR2305990.pdf