Virus-MNIST: A Benchmark Malware Dataset

2021-02-28 · David Noever, Samantha E. Miller Noever

The short note presents an image classification dataset consisting of 10 executable code varieties and approximately 50,000 virus examples. The malicious classes include 9 families of computer viruses and one benign set. The image formatting for the first 1024 bytes of the Portable Executable (PE) mirrors the familiar MNIST handwriting dataset, such that most of the previously explored algorithmic methods can transfer with minor modifications. The designation of 9 virus families for malware derives from unsupervised learning of class labels; we discover the families with KMeans clustering that excludes the non-malicious examples. As a benchmark using deep learning methods (MobileNetV2), we find an overall 80% accuracy for virus identification by families when beneware is included. We also find that once a positive malware detection occurs (by signature or heuristics), the projection of the first 1024 bytes into a thumbnail image can classify with 87% accuracy the type of virus. The work generalizes what other malware investigators have demonstrated as promising convolutional neural networks originally developed to solve image problems but applied to a new abstract domain in pixel bytes from executable files. The dataset is available on Kaggle and Github.

📄 PDF Abstract BibTeX arXiv:2103.00602

Code (0)

등록된 구현이 없습니다.

Tasks

Clusteringimage-classification Image Classification Malware Detection

Virus-MNIST: Machine Learning Baseline Calculations for Image Classification

2021-11-03 · Erik Larsen, Korey MacVittie, John Lilly

The Virus-MNIST data set is a collection of thumbnail images that is similar in style to the ubiquitous MNIST hand-written digits. These, however, are cast by reshaping possible malware code into an image array. Naturall…

Benchmarking BIG-bench Machine Learning Classification image-classification+1

Benchmark Static API Call Datasets for Malware Family Classification

2021-11-30 · Berkant Düzgün, Aykut Çayır, Ferhat Demirkıran, Ceyda Nur Kahya 외

Nowadays, malware and malware incidents are increasing daily, even with various antivirus systems and malware detection or classification methodologies. Machine learning techniques have been the main focus of the securit…

Classification Malware Classification Malware Detection

Behavioral Malware Classification using Convolutional Recurrent Neural Networks

2018-11-19 · Bander Alsulami, Spiros Mancoridis

Behavioral malware detection aims to improve on the performance of static signature-based techniques used by anti-virus systems, which are less effective against modern polymorphic and metamorphic malware. Behavioral mal…

Behavioral Malware Classification Behavioral Malware Detection Classification Diversity+3

Adapting Novelty towards Generating Antigens for Antivirus systems

2025-05-24 · Ritwik Murali, C Shunmuga Velayutham

It is well known that anti-malware scanners depend on malware signatures to identify malware. However, even minor modifications to malware code structure results in a change in the malware signature thus enabling the var…

Evolutionary Algorithms Malware Analysis Malware Detection

A Malware Obfuscation AI Technique to Evade Antivirus Detection in Counter Forensic Domain

2020-09-24 · Enabling AI Applications in Data Science. Studies in Computational Intelligence, vol 911. Springer, Cham. 2020 9 · Ahmed A. Mawgoud, Hussein M. Rady, Benbella S. Tawfik

Data obfuscation is the process of converting a constant or a variable into computational results of several constants to make it hard for the files to be detected or analyzed by anti-malware engines. In recent years, ma…