• Mrs. R. S. Deshpande
• Mrs. P. A. Mishra
• Ms. D. R. Jawale

Rapid advancements in network technology come at the cost of insecure data. The intruder is attempting to read data being transmitted across the network. The goal behind reading the data is to observe packets and produce traffic in order to disrupt communication. Various studies are being conducted in order to detect and prevent these assaults from occurring on the network. To detect network threats, intrusion detection techniques such as fuzzy clustering, genetic algorithms, artificial neural networks, and others are utilised. ANN is the approach with the best detection rate among these. The back propagation algorithm of the Multilayer Perceptron and SVM are used in this system. These methods are used in these techniques. The intruder's whereabouts is tracked using a self-organizing map. As a consequence, the method is 90.43 percent efficient. The suggested system is made up of several modules, such as packet collection across the network, data preprocessing, and feature extraction. The suggested system consists of several modules, including packet collecting over the network, data preparation (i.e., extracting the feature to apply), and classification of the connection as normal or assault. We can either kill the process or shut down the system completely. Alternatively, we can use SOM to track down the location of that IP address.

MLP, DDOS, NIDES, ANN, ISA, Back Propagation Network

"Detection and Classification of Attacks in NIDS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.8, Issue 12, page no.e414-e417, December-2021, Available :http://www.jetir.org/papers/JETIR2112453.pdf

"Detection and Classification of Attacks in NIDS", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.8, Issue 12, page no. ppe414-e417, December-2021, Available at : http://www.jetir.org/papers/JETIR2112453.pdf