Skripsi
KLASIFIKASI PDF MALWARE PADA GARBA RUJUKAN DIGITAL (GARUDA) KEMDIKBUD DIKTI DENGAN METODE LOGISTIC REGRESSION
Malware that can enter through PDF files that appear unsuspicious is one of the main factors in cyber security attacks. The GARUDA dataset was analyzed statically using VirusTotal and PDFiD to identify whether a PDF file is dangerous or not, then classification was carried out to determine the characteristics of the PDF file using the Logistic Regression method of the Multinomial type. The dataset used consists of 10,000 PDF format files with 21 prediction variables and there are 3 class categories. The GARUDA dataset has unbalanced data, therefore a Random Oversampling technique is used to overcome it. The results show that the Multinomial Logistic Regression model is able to achieve an accuracy of 93%. These results indicate that the model has reliable performance in performing classification.
Inventory Code | Barcode | Call Number | Location | Status |
---|---|---|---|---|
2407003797 | T147784 | T1477842024 | Central Library (REFERENCES) | Available but not for loan - Not for Loan |
No other version available