Malware images: visualization and automatic classification

By Lakshmanan Nataraj, Shanmugavadivel Karthikeyan, G. Jacob, Bangalore S. Manjunath. Visualization for Computer Security, 2011

1,333 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Signal Processing

View Paper: https://www.semanticscholar.org/paper/87ff7ef37bd35d97ea0316398e762cd642df64a6

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

1. Kim-Kwang Raymond Choo
2. Robert Brandon
3. Charles K. Nicholas
4. Dmitry Ulyanov
5. Yang Cao
6. Zhihua Cui
7. Giorgio Giacinto
8. Ali Dehghantanha

In Computer Vision and Pattern Recognition

1. Bryan Catanzaro
2. Dmitry Ulyanov
3. Yang Cao
4. Luc Van Gool
5. Robert Brandon
6. Charles K. Nicholas
7. Giorgio Giacinto
8. Ali Dehghantanha

In Signal Processing

1. Kim-Kwang Raymond Choo
2. Nikola Milosevic
3. Dmitry Ulyanov
4. Divya Bansal
5. Giorgio Giacinto
6. Ali Dehghantanha
7. Sanjeev Sofat
8. Bryan Catanzaro

Citations in the corpus

• Malware Classification with Deep Convolutional Neural Networks (2018, methodology): “Note that previous work [5] showed that malware belonging to same family are visually similar, which is beneficial with respect to the capacity for a CNN to detect relevant patterns.”
• Detection of Malicious Code Variants Based on Deep Learning (2018, methodology): “Table I, taken from [19], presents some recommended image widths for various file sizes, based on empirical observations.”
• Malware Analysis and Classification: A Survey (2014, methodology): “[28] proposed a method for visualizing and classifying malwares using image processing techniques, which visualize malware binaries as gray-scale images.”
• Robust Intelligent Malware Detection Using Deep Learning (2019, methodology): “We performed a comparative study by employing classical MLAs and deep learning algorithms on the benchmark datasets, Malimg [17], [33] and privately collected malware samples.”
• Machine learning aided Android malware classification (2017, methodology): “In [17], pattern recognition techniques are used to detect malware, while other works used standard machine learning algorithms such as perception, SVM, locality sensitive hashing and decision trees to assist in malware analysis (see [18]).”
• Malware Detection by Eating a Whole EXE (2017, methodology): “This technique was developed to try and exploit early image-processing approaches as a way of visualization, and then for malware family classification (Nataraj et al. 2011b).”
• Novel Feature Extraction, Selection and Fusion for Effective Malware Family Classification (2015, methodology): “An original way to represent a malware sample is to visualize the byte code by interpreting each byte as the gray-level of one pixel in an image [35].”