SaTC: CORE: Small: Automated Dynamic Analysis for Smart Device Malware Hiding Mechanisms

点击翻译按钮获取中文摘要

Smart devices range from smartphone to smart watch and tablets. While smart devices bring new functions and possibilities to users, they also open a “Pandora’s Box” of potential problems, from eavesdropping attacks to erasing data on a user’s storage device. There has been a significant increase in the number of malicious apps as our daily life increasingly relies on mobile applications. The project's novelties are to develop automated techniques to comprehensively uncover distinguishing behaviors of malicious apps. The project's broader significance and importance are to help billions of users of smart devices to recognize malicious apps and thereby prevent them from becoming victims of cyber-attacks. Moreover, the project generates an empirical experimental platform for the research community and includes educational activities involving high school students.This project's technical efforts involve two steps. The first is developing a multimedia-based automated testbot, which exploits multimedia (e.g., vision, audio, vibration) recognition algorithms to mimic the user to automatically test applications and find self-hiding behaviors on smart devices. With analysis results from the testbot, the second step creates natural language processing and static program analysis algorithms to find code snippets of unknown self-hiding behaviors of smart device malware and generates technique descriptions based on these code snippets, which in turn benefits the research and industry communities.This project is jointly funded by the Secure & Trustworthy Cyberspace program (SaTC) and the Established Program to Stimulate Competitive Research (EPSCoR).This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.