Malware Detection Framework using Big Data Tools - Spark
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
src
.gitignore
DatasetDetails.csv
Notes.txt
README.md
build.sbt
metadata.csv
selectFiles.py

README.md

Malware Detection Framework Using Static Analysis Approach

High Level Design:

1. Training

Feature Extraction
Feature Selection
Creating Machine Learning Model

2. Testing

Build Test Dataset
Predict using Machine Learning Model
Generate Metrics

Modules:

com.spark.malware (package)

Training

ExtractFeatures.scala
     Extract Ngrams
SelectFeatures.scala
     build feature set with k features (based on IG or PCA or SVD method)
BuildDataset.scala
     Build training/test dataset
BuildModel.scala
     Build Machine learning model

Common

RunParameters.scala
Utilities.scala

Controller

DetectMalwareController.scala
     Main routine that controlls the flow of the application