# Generation & Evaluation of Adversarial Examples for Malware Obfuscation

## TL;DR

This paper introduces a generative model for creating adversarial malware examples through obfuscation, achieving high evasion rates against classifiers while maintaining functionality.

## Contribution

It presents a novel generative approach for malware obfuscation that effectively evades neural network classifiers in both white-box and black-box scenarios.

## Key findings

- Achieves up to 100% misclassification in white-box settings.
- Achieves up to 98% misclassification in black-box settings.
- Demonstrates transferability of adversarial examples across models.

## Abstract

There has been an increased interest in the application of convolutional neural networks for image based malware classification, but the susceptibility of neural networks to adversarial examples allows malicious actors to evade classifiers. Adversarial examples are usually generated by adding small perturbations to the input that are unrecognizable to humans, but the same approach is not effective with malware. In general, these perturbations cause changes in the byte sequences that change the initial functionality or result in un-executable binaries. We present a generative model for executable adversarial malware examples using obfuscation that achieves a high misclassification rate, up to 100% and 98% in white-box and black-box settings respectively, and demonstrates transferability. We further evaluate the effectiveness of the proposed method by reporting insignificant change in the evasion rate of our adversarial examples against popular defense strategies.