2015 Fourth International Conference on Cyber Security, Cyber Warfare, and Digital Forensic (CyberSec) 2015
DOI: 10.1109/cybersec.2015.28
|View full text |Cite
|
Sign up to set email alerts
|

Packet Header Intrusion Detection with Binary Logistic Regression Approach in Detecting R2L and U2R Attacks

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1
1

Citation Types

0
3
0

Year Published

2019
2019
2024
2024

Publication Types

Select...
3
3
1
1

Relationship

0
8

Authors

Journals

citations
Cited by 10 publications
(3 citation statements)
references
References 14 publications
0
3
0
Order By: Relevance
“…The main advantage of logistic regression is its simplicity and interpretability, which allows us to understand the influence of features on classification. However, the main limitation of this method is the assumption of a linear relationship between the features and the target variable, which may limit the model's ability to correctly describe complex nonlinear relationships [14,15].…”
Section: Overview Of Approaches and Methodsmentioning
confidence: 99%
“…The main advantage of logistic regression is its simplicity and interpretability, which allows us to understand the influence of features on classification. However, the main limitation of this method is the assumption of a linear relationship between the features and the target variable, which may limit the model's ability to correctly describe complex nonlinear relationships [14,15].…”
Section: Overview Of Approaches and Methodsmentioning
confidence: 99%
“…The ratio of data amounts between the two approaches is 1000 to 1. The class imbalance issue will significantly impact Convolutional Neural networks [13]. The system's best accuracy rate can still be 98.9%, even if it cannot recognize U2R assaults.…”
Section: ░ 3 Proposed Methodologymentioning
confidence: 99%
“…Because IDS needs to be updated to adjust to the changing environment, the network's diverse and flexible nature significantly shortens the lifetime of detection models.Depending on unique expenses related to computation, money, and time, distributed, centralized, and hybrid approaches must be used.Because of the aforementioned difficulties, current conventional procedures are unable to attain the necessary high-level accuracy. A more through, detailed, and in-depth understanding of the types of intrusion occurrences is needed to guarantee the effectiveness of intrusion detection systems.Network intrusion detection systems have made extensive use of traditional machine learning techniques, including Bayesian [8][9][10], Support Vector Machines [11][12][13][14][15][16], Decision Trees [17][18][19], Logistic Regression [20][21][22][23], and others. These techniques have produced favorable results.…”
Section: Figure I General Architecture Of Industrial Control Systemmentioning
confidence: 99%