• Dr. Narendra Kandoi

Technology, procedures, & controls used in cyber security are aimed at preventing cyber-attacks on systems, networks, programs, devices, & data. Its goal is to safeguard systems, networks, & technology against unauthorized use and cyber-attacks. Using a Network Attack Detection System, network security breaches may be detected & contained in companies. Creating a flexible & effective network intrusion detection system (NIDS) for unexpected & unanticipated assaults, on the other hand, poses numerous difficulties. A hybrid ID architecture built on DL-based prediction & classification of destructive network cyberattacks & protection of security is developed in this article using an AlexNet. The CNN pretrained Alexnet uses convolution to collect local features, while the recurrent neural network (RNN) catches temporal data to enhance the efficiency & predictions of the ID system. The hybrid method HARNN ensures that no intrusive packets transmit thru and enter our systems by using a combination of techniques. The hybrid convolution RNN intrusion detection system was tested using publicly accessible ID data, including the contemporary & realistic CSE-CIC-DS2018 data. Using 10-fold cross-validation, the simulation outcomes indicate that the suggested network attack detecting system surpasses existing ID methods in terms of malicious assault identification rate accuracy using CSE-CIC-IDS2018 data.

Cyber Security; Recurrent neural network; deep learning; AlexNet; intrusion detection system; machine learning.

"Network Attack Detection System Based on Hybrid Deep Learning Technique in Cyber Security Application", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 4, page no.816-825, April-2019, Available :http://www.jetir.org/papers/JETIR1904U06.pdf

"Network Attack Detection System Based on Hybrid Deep Learning Technique in Cyber Security Application", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 4, page no. pp816-825, April-2019, Available at : http://www.jetir.org/papers/JETIR1904U06.pdf