Abstract
Malicious code (malware) is used to steal sensitive data, to attack corporate networks, and to deliver spam. To silently compromise systems and maintain their access, malware developers usually apply obfuscation techniques that result in a massive amount of malware variants and that can render static analysis approaches ineffective. To address the limitations of static approaches, researchers have proposed dynamic analysis systems. These systems usually rely on a sandboxing environment that captures the system calls performed by a program under analysis. In this paper, we propose a novel approach to capture and model malware behavior that is based on the monitoring of the data values that a certain subset of instructions writes to memory during program execution. We have implemented a malware clustering component and a component to detect code reuse between different malware families. To validate our proposed techniques, we analyzed 16,248 malware samples. We found that our techniques produce clusters with high accuracy, as well as interesting cases of code reuse among malicious programs.
Paper version not known (Free)
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.