INTERNATIONAL JOURNAL OF NOVEL RESEARCH AND DEVELOPMENT International Peer Reviewed & Refereed Journals, Open Access Journal ISSN Approved Journal No: 2456-4184 | Impact factor: 8.76 | ESTD Year: 2016
Scholarly open access journals, Peer-reviewed, and Refereed Journals, Impact factor 8.76 (Calculate by google scholar and Semantic Scholar | AI-Powered Research Tool) , Multidisciplinary, Monthly, Indexing in all major database & Metadata, Citation Generator, Digital Object Identifier(DOI)
The necessity for networking and data exchange has dramatically increased in the modern world. Network security is necessary given the rapid development and globalization of information technology. Although they may offer some amount of security, firewalls never warn administrators of impending assaults. A trustworthy detection system is required to locate such aberrant network packet behavior in order to increase efficiency and accuracy. As a result of how quickly today's network environment is evolving, the network is constantly at risk from new sorts of attacks. Therefore, regular updates to the network administration system are required for upgrading the security level. Intrusion Detection Systems is one of the network packet monitoring systems (IDS). The proposed model was created using a machine learning approach to identify malicious network packet activity. KDD-99 dataset is utilized for that. The dataset is first normalized to reduce calculation complexity, and then further features are reduced using a Deep Neural Network technique. Only effective features can be employed for harmful behavior identification, according to the reduced features. According to the results analysis, DNN works best when choosing more than 15 features, whereas co-relation performs best when choosing less than 15. The k-mean clustering algorithm is used to accomplish data clustering after feature reduction. Deep Neural Network, are designed for classification of dataset into five attack categories i.e. DOS, U2R, R2L, Probe and Normal. As compared to some other multilevel classifier work the proposed algorithm proves its efficiency in terms of high accuracy, high detection rate and False Alarm Rate (FAR).
Keywords:
SDN, Random Forest Classifier, Intrusion Detection System, KNN Clustering
Cite Article:
"Detection and Elimination of Network Anomaly in SDN using Trust Analysis", International Journal of Novel Research and Development (www.ijnrd.org), ISSN:2456-4184, Vol.8, Issue 5, page no.d247-d252, May-2023, Available :http://www.ijnrd.org/papers/IJNRD2305335.pdf
Downloads:
000118751
ISSN:
2456-4184 | IMPACT FACTOR: 8.76 Calculated By Google Scholar| ESTD YEAR: 2016
An International Scholarly Open Access Journal, Peer-Reviewed, Refereed Journal Impact Factor 8.76 Calculate by Google Scholar and Semantic Scholar | AI-Powered Research Tool, Multidisciplinary, Monthly, Multilanguage Journal Indexing in All Major Database & Metadata, Citation Generator
Facebook Twitter Instagram LinkedIn