A Machine-learning Approach for Classifying and Categorizing Android Sources and Sinks
Download: Paper (PDF)
Date: 22 Feb 2014
Document Type: Briefing Papers
Additional Documents: Slides
Associated Event: NDSS Symposium 2014
In this paper we propose SUSI, a novel machine-learning guided approach for identifying and categorizing previously unknown privacy-sensitive sources and sinks directly from the code of any Android API (e.g., Android 4.3 or GoogleGlass). Our results improve both static and dynamic analysis tools in detecting malicious information flows more completely.