Efficient Intrusion Detection of Imbalenced Network Traffic using Deep Learning

Nayan kumar V; Punith kumar M; Tejas Kumar K; Vinod Kumar S; Dr. Aruna M.G

Efficient Intrusion Detection of Imbalenced Network Traffic using Deep Learning

Authors: Nayan kumar V, Punith kumar M, Tejas Kumar K, Vinod Kumar S, Dr. Aruna M.G

Unique Paper ID: 156173
Volume: 9
Issue: 2
PageNo: 1048-1054

Keywords: RandomForest Alxenett Lstm DSSTE algorithm

Abstract:
In imbalanced network traffic, malicious cyber-attacks can often hide in large amounts of normal data. At Cyberspace, using a high level of encryption and making it difficult for NIDS to ensure accuracy and timeliness. Despite decades of development, IDSs still face challenges in improving in detection accuracy. Deep Learning is a branch of Machine learning, whose performance is remarkable and as a hotspot in field of research.This paper involves both machine learning and Deep learning for intrusion detection in imbalanced network traffic.this process a DSSTE algorithm to avoid imbalance problems.initially the training set is preprocessed to modify imbalanced data and features are extracted. Then newly obtained training set is fed to a various classification models to evaluate that proposed DSSTE algorithm outperforms other methods.

Download article

email to a friend

Cite This Article

ISSN: 2349-6002
Volume: 9
Issue: 2
PageNo: 1048-1054

Efficient Intrusion Detection of Imbalenced Network Traffic using Deep Learning

Available:https://ijirt.org/Article?manuscript=156173

Impact Factor
8.01 (Year 2024)

UGC Approved
Journal no 47859

Join Our IPN

IJIRT Partner Network

Submit your research paper and those of your network (friends, colleagues, or peers) through your IPN account, and receive 800 INR for each paper that gets published.

Join Now