Asset Details
Do you wish to reserve the book?
Effective network intrusion detection by addressing class imbalance with deep neural networks multimedia tools and applications
Hey, we have placed the reservation for you!
By the way, why not check out events that you can attend while you pick your title.
Oops! Something went wrong.
Looks like we were not able to place the reservation. Kindly try again later.
Are you sure you want to remove the book from the shelf?
Effective network intrusion detection by addressing class imbalance with deep neural networks multimedia tools and applications
Do you wish to request the book?
Effective network intrusion detection by addressing class imbalance with deep neural networks multimedia tools and applications
Please be aware that the book you have requested cannot be checked out. If you would like to checkout this book, you can reserve another copy
We have requested the book for you!
Your request is successful and it will be processed during the Library working hours. Please check the status of your request in My Requests.
Oops! Something went wrong.
Looks like we were not able to place your request. Kindly try again later.
Journal Article
Effective network intrusion detection by addressing class imbalance with deep neural networks multimedia tools and applications
2022
Overview
The Intrusion Detection System plays a significant role in discovering malicious activities and provides better network security solutions than other conventional defense techniques such as firewalls. With the aid of machine learning-based techniques, such systems can detect attacks more accurately by identifying the relevant data patterns. However, the nature of network data, time-varying environment, and unknown occurrence of attacks made the learning task very complex. We propose a deep neural network that utilizes the classifier-level class imbalance solution to solve this problem effectively. Initially, the network data is preprocessed through data conversion followed by the min-max normalization method. Then, normalized data is fed to neural network where the cross-entropy function is modified to address the class imbalance problem. It is achieved by weighting the classes while training the classifier. The extensive experiments are performed on two challenging datasets, namely NSL-KDD and UNSW-NB15, to establish the superiority of the proposed approach. It includes comparisons with commonly employed imbalance approaches such as under-sampling, over-sampling, and bagging as well as existing works. The proposed approach attains 85.56% and 90.76% classification accuracy on NSL-KDD and UNSW-NB15 datasets, respectively. These outcomes outperformed data-level imbalance methods and existing works that validate the need to incorporate class imbalance for network traffic categorization.
Publisher
Springer US,Springer Nature B.V
