As the information systems are upgrading with the new technologies and becoming technology driven, the chance of getting intrude is also increasing at an unprecedented rate. To curb such activities of malpractices, the intrusion detection system is used to protect the sensitive and confidential data. In this paper, different types of intrusion detection techniques are reviewed and encompass how deep neural networks are deploying better accuracy when compared to classical machine learning techniques. Deep neural networks have been taken into force for intrusion detection with a learning rate of 0.1 and it has been executed for 1000 iterations. The dataset used for training purposes is KDDCup-‘99’ and the results were compared to traditional machine learning algorithms that are trained with the same dataset in DNN layers from one to five. Paper is not associated with research work rather than a comparison of different techniques.
Evaluation of Deep Neural Networks for Advanced Intrusion Detection Systems
2020-11-05
259955 byte
Conference paper
Electronic Resource
English
British Library Online Contents | 2003
|