Intrusion Detection System Using Generative Unique Adversarial Neural Network in cloud Environment
K. Srujan Raju, Pedhoori Rashmitha, Kolluru Venkata Nagendra, Srinivasarao Dharmireddi, M Rekha, S. V. S. V. Prasad Sanaboina
Abstract
Intrusion detection is an important part of a company's infrastructure security. However, one challenge of intrusion detection in cloud computing is the large volume of data that must be processed in real-time. Existing system not predict the IDS perfect on cloud. Suggest using deep learning technology to create an intrusion detection system (IDS) preprocessing, and feature selection in order to improve the security level accuracy of cloud storage systems. To resolve the problem, in this paper we introduce the Generative Unique Adversarial Neural(GUNN). We gather kddcup99 dataset from kaggle relevant record, and pre-processing using grey wolf optimization algorithm to remove noisy or irrelevant data and identify pertinent features from the data. Then another process of feature selection framework based support vector machine, this algorithm is used select the feature section of data. Finally the result for the intrusion detection system (IDS) increases the classification accuracy is 94.5%. The proposed method used predict IDS in cloud environment high precision, recall and F1 measurement.