Unleashing the Adversarial Facet of Software Debloating

TL;DR

This paper investigates how software debloating techniques can be exploited as adversarial tools to deceive machine learning malware classifiers, revealing new security vulnerabilities.

Contribution

It demonstrates that debloating can be used to generate adversarial examples that reduce malware detection effectiveness, highlighting a novel security concern.

Findings

Debloating techniques can generate effective adversarial malware samples.

Adversarial examples decrease VirusTotal detection rates.

Highlights new security risks in software debloating applications.

Abstract

Software debloating techniques are applied to craft a specialized version of the program based on the user's requirements and remove irrelevant code accordingly. The debloated programs presumably maintain better performance and reduce the attack surface in contrast to the original programs. This work unleashes the effectiveness of applying software debloating techniques on the robustness of machine learning systems in the malware classification domain. We empirically study how an adversarial can leverage software debloating techniques to mislead machine learning malware classification models. We apply software debloating techniques to generate adversarial examples and demonstrate these adversarial examples can reduce the detection rate of VirusTotal. Our study opens new directions for research into adversarial machine learning not only in malware detection/classification but also in other software domains.