Investigation of Machine Learning Algorithms for Malware Detection in PE and PDF Files - Configuration Manual

Sep 17, 2026

Uploaded by Noah

Configuration manual for a MSc cybersecurity research project on building machine learning models for malware detection across PE and PDF file types. It defines the required software and hardware environment, including Windows 10 (64-bit), HP hardware, WEKA 3.8.6, Excel, and Oracle VM. It documents dataset selection (Evasive PDFMal2022 and WinMal), preprocessing steps such as removing NaN rows, filtering corrupted records, and excluding API_Functions due to size constraints, then describes classifier setup using WEKA with 10-fold cross validation and supervised models.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages11

Reading Time28 min

AccessFree to download

1 Introduction

2 System Configuration

2.1 Hardware Requirement

2.2 Software Requirement

3 Project Implementation

3.1 Data Preprocessing

3.2 Data Mining

4.0 Conclusion

Configuration Manual Investigation of Machine Learning Algorithms for Malware Detection in PE and PDF Files Masters in Cybersecurity Rosemary Usoroh Student ID: x21114374 School of Computing National College of Ireland Supervisor: Arghir-Nicolae Moldovan National College of Ireland MSc Project Submission Sheet School of Computing Student Name: ROSEMARY USOROH Student ID: x21114374 Programme: MASTER OF SCIENCE IN CYBERSECURITY Year: 2024 Module: Msc Research Project Lecturer: Arghir-Nicolae Moldovan Submission Due Date: 31-01-2024 Investigation of Machine Learning Algorithms for Malware Project Title: Detection in PE and PDF Files Word Count: 926 Page Count: 10 I hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project. ALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author's written or electronic work is illegal (plagiarism) and may result in disciplinary action. Signature: ROSEMARY USOROH Date: 31-01-2024 PLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST | Attach a completed copy of this sheet to each project (including multiple copies) | □ | | --- | --- | | Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ | | You must ensure that you retain a HARD COPY of the project, both for your own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | □ | Assignments that are submitted to the Programme Coordinator Office must be placed into the assignment box located outside the office. | Office Use Only | | | --- | --- | | Signature: | | | Date: | | | Penalty Applied (if applicable): | | Configuration Manual Rosemary Usoroh Student ID: x21114374 1 Introduction This configuration manual presents the requirements for creation of machine learning models in the detection of malware. The manual will give explanation of the software and hardware components that are needed for the completion of this project. 2 System Configuration 2.1 Hardware Requirement The table below presents the hardware configuration used for the implementation of this project; | Hardware | Configuration | | --- | --- | | System | HP | | Operating System | Windows 10(64 Bits) Pro | | RAM | 12GB | | Hard Disk | 1TB | | Processor | Intel Core i5-10210U | Table 1 : Hardware requirement Figure 1: Operating System Configuration 2.2 Software Requirement | Software | Version | | --- | --- | | WEKA | 3.8.6 | | Excel | 2310 | | Oracle VM Machine | 7.0.12 | Table 2: Software requirements Figure 2: WEKA, Virtual Machine and Excel software 3 Project Implementation The datasets used for this project are in the artefacts. This section will provide a summarized implementation of the research and pictorial presentation of the implementation. Figure 3: The figure above shows one of the dataset in the excel sheet. In this research, four malware datasets were analyzed for this research. The first datasets was evasive PDF dataset (Evasive-PDFMal2022), it was downloaded from (Issakhani et al., 2022) . The original file that was downloaded was in a CSV format. The second malware dataset which is Windows PE Malware (WinMal) samples was downloaded from (Yousuf et al., 2023) . The samples were divided into four different parts which includes Imported DLLs, API Functions, PE Header and PE Section. The original files of these samples were all downloaded in CSV format. 3.1 Data Preprocessing The Evasive PDFMal2022 and WinMal datasets came in a structured format, therefore needs little preprocessing. In the Evasive PDFMal2022, the row

FAQs

What models and validation method are used for the malware detection project?

The project uses supervised machine learning algorithms including PART Rule, an Ordinal Class Classifier, and Bayes Net, with 10-fold cross validation for the malware analysis.

Which datasets are analyzed for PE and PDF malware detection?

Four malware datasets are analyzed, including the evasive PDFMal2022 dataset and the Windows PE malware (WinMal) samples split into Imported DLLs, API Functions, PE Header, and PE Section.

What preprocessing steps are applied before running classifiers in WEKA?

For PDFMal2022, rows with NaN and inaccurate or corrupted data are removed. For WinMal, the API_Functions feature set is excluded due to dataset size, and the SHA column is removed in WEKA to improve classification accuracy.

Sep 17, 2026

Uploaded by Noah