2020
DOI: 10.1111/coin.12342
|View full text |Cite
|
Sign up to set email alerts
|

An empirical model in intrusion detection systems using principal component analysis and deep learning models

Abstract: Data are a main resource of a computer system, which can be transmitted over network from source to destination. While transmitting, it faces lot of security issues such as virus, malware, infection, error, and data loss. The security issues are the attacks that have to be detected and eliminated in efficient way to guarantee the secure transmission. The attack detection rates of existing Intrusion Detection Systems (IDS) are low, because the number of unknown attacks are high when compared to the known attack… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
4
1

Citation Types

0
5
0

Year Published

2021
2021
2024
2024

Publication Types

Select...
8

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(5 citation statements)
references
References 23 publications
0
5
0
Order By: Relevance
“…FS method is viewed as perhaps the most essential technique which is applied in network security, especially in IDS. IDS is needed to manage tremendous volume of data that are likely made up of random, repetitive, and redundant features [32]. The main explanation behind the slowdown of the training and testing process can be because of logical inconsistency in features data, which brings about expanded resource consumption, just as in the decline of the execution of classification precision, and subsequently, rate of detection becomes low [33].…”
Section: Related Workmentioning
confidence: 99%
See 1 more Smart Citation
“…FS method is viewed as perhaps the most essential technique which is applied in network security, especially in IDS. IDS is needed to manage tremendous volume of data that are likely made up of random, repetitive, and redundant features [32]. The main explanation behind the slowdown of the training and testing process can be because of logical inconsistency in features data, which brings about expanded resource consumption, just as in the decline of the execution of classification precision, and subsequently, rate of detection becomes low [33].…”
Section: Related Workmentioning
confidence: 99%
“…In [32] developed a hybrid model for network IDS that includes a combined approach Principle Component Analysis and Deep Learning (PCA DL) to improve attack detection. By evaluating the method using KDD-CUP 99 dataset it has achieved a 92% accuracy in detecting the attacks.…”
Section: Related Workmentioning
confidence: 99%
“…Furthermore, the IoT-ID20 dataset is used for training purposes [ 45 ]. Another effective threat classification scheme is presented [ 46 ], where authors mainly target the less frequently occurring suspicious events in industrial networks. They have observed the real-life scenario for a sustainable period and have organized a customized dataset.…”
Section: Related Workmentioning
confidence: 99%
“…The practical results imply that this strategy can increase malware detection and classifier classification performance. In [17], H. Rajadurai and U. D. Gandhi,2021, The Principle Component Analysis and Deep Learning (PCA-DL) methodology are presented in this paper as a hybrid technique. The suggested PCA-DL technique has a 92.6 percent accuracy rate in accurately detecting malicious.…”
Section: Related Workmentioning
confidence: 99%