2022
DOI: 10.1109/access.2022.3171912
|View full text |Cite
|
Sign up to set email alerts
|

Malware Detection Using LightGBM With a Custom Logistic Loss Function

Abstract: The increased spread of malicious software (malware) through the internet remains a serious threat. Malware authors use obfuscation and deformation techniques to generate new types than can evade traditional detection methods. Hence, it is widely expected that machine learning methods can classify malware and cleanware based on the characteristics of malware samples. This paper investigates malware classification accuracy using static methods for malware detection based on LightGBM by a custom log loss functio… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
3
1
1

Citation Types

0
6
0

Year Published

2022
2022
2024
2024

Publication Types

Select...
6
2

Relationship

0
8

Authors

Journals

citations
Cited by 11 publications
(6 citation statements)
references
References 29 publications
0
6
0
Order By: Relevance
“…(d) Decision trees [7] are another ML technique that has been frequently employed in combination with other supportive algorithms for malware detection. (e) Logistic regression [8] is a statistical method used to figure out how likely a binary outcome is to happen. It has been used successfully in programs that look for malware.…”
Section: The Role Of Machine Learning In Ransomware Defensementioning
confidence: 99%
“…(d) Decision trees [7] are another ML technique that has been frequently employed in combination with other supportive algorithms for malware detection. (e) Logistic regression [8] is a statistical method used to figure out how likely a binary outcome is to happen. It has been used successfully in programs that look for malware.…”
Section: The Role Of Machine Learning In Ransomware Defensementioning
confidence: 99%
“…An investigation to classification accuracy of malware was done by [35]. The process is done using custom log loss function and Based on LightGBM.…”
Section: Related Workmentioning
confidence: 99%
“…The best results in the model are obtained with the weighted rank voting method according to class accuracies. In the study [15], a malware detection model using LightGBM with a special log loss function is presented. The accuracy performances of static methods were examined within the scope of malware detection.…”
Section: Related Workmentioning
confidence: 99%
“…Euh et al [11] Original dataset Extra Gradient Boosting (XGB) Accuracy (WEM)-100% Accuracy (API)-94.7% Cohen et al [12] Original dataset LightGBM Accuracy-95.1% Singh et al [13] Original dataset AdaBoost (ADAB) Accuracy-99.54% Gupta et al [14] Original dataset Bagging Accuracy-99.5% TPR-99.6% Gao et al [15] EMBER 2017 LightGBM Accuracy-99.81% (EMBER) FFRI Accuracy-99.84 %(FFRI) Kumar et al [16] Original dataset Random Forest (RF), LightGBM, XGB, Extra Trees (EXT) Accuracy-98.49% [18] Original dataset K-mode, Bagging Accuracy-99.41% F1 Score-99.13% Yang et al [19] Datacon 2019 t-SNE, Stacking Accuracy-99.67% F1 Score-99.67% Appice et al [20] Original dataset K-means++, Stacking Sensitivity-96% AUC-96.6% Ramadhan et al [21] BODMAS Bagging (LightGBM, XGB, Logistic Accuracy-99.63% regression)…”
Section: Table 1: Related Workmentioning
confidence: 99%