作者: Li Li , Kevin Allix , Daoyuan Li , Alexandre Bartel , Tegawende F. Bissyande
DOI: 10.1109/QRS.2015.36
关键词:
摘要: We discuss the capability of a new feature set for malware detection based on potential component leaks (PCLs). PCLs are defined as sensitive data-flows that involve Android inter-component communications. show common in apps and malicious applications indeed manipulate significantly more than benign apps. Then, we evaluate machine learning-based approach relying PCLs. Experimental validations high performance identifying malware, demonstrating can be used discriminating from