OpenSec Atlas

Linux-Malware-Detection-Research: An Open Source Tool for Endpoint Security | OpenSec Atlas

Endpoint Security

Tool

Linux-Malware-Detection-Research

A research-focused Linux malware detection tool that combines multiple pretrained AI models to classify ELF files as benign or malicious.

Visit Website View on GitHub

About This Tool

A collection of Linux Malware Detection projects (research paper implementations) done by me.

Primary Use Case

This tool is designed for researchers and security analysts to analyze Linux ELF binaries for malware detection using AI-based models. It is useful for evaluating and experimenting with different machine learning approaches on Linux malware datasets to improve endpoint protection.

Key Features

Combines outputs of three pretrained AI models for malware classification
Supports end-to-end feature extraction from ELF files
Generates combined feature set CSV for analysis
Implements research paper methodologies for Linux malware detection
Integrates with WEKA-3.6 machine learning toolkit
Supports both Python 2.7 and Java 8+ environments

Insights & Recommendations

Ensure Python 2.7 and Java 8+ are properly installed as the tool relies on both environments. WEKA-3.6 toolkit is required for machine learning operations. The tool is research-oriented and may require familiarity with ELF file formats and machine learning concepts for effective use.

Installation

Install Python 2.7
Install Java 8.0 or higher
Download and install WEKA-3.6 toolkit
Clone the repository
Place the ELF file to be tested in the elf/ directory

Usage

make

Runs all three projects on the ELF file in elf/ directory to generate a combined feature set CSV and performs malware classification using pretrained models.

Smart Usage Notes

Integrate this tool into endpoint detection platforms for enhanced Linux malware identification.Use combined AI model outputs to reduce false positives in malware alerts.Leverage generated CSV feature sets for training custom ML models tailored to specific environments.Incorporate into purple team exercises to simulate AI-driven malware detection and evasion scenarios.Automate batch scanning of ELF binaries in CI/CD pipelines to prevent deployment of malicious code.