Android Application Evolution and Malware Detection

Speaker/Bio

Prof. Zhang is an assistant Professor in Computer Science Department at BU Metropolitan College. Her past research mainly focuses on the system resource management. Her current research focuses on mobile security.

Abstract

Android has dominated the mobile market for a few years now, and continues to increase its market share. Meanwhile, Android has seen a sharper increase in malware. In this talk, I will first discuss our analysis on application security evolution. The data shows that more than half applications have security vulnerabilities and/or dangerous behaviors. The security problems remain or even worse in the updated versions of most applications. Then, I will discuss malware detection using classification techniques. Our permissions-based classification model can achieve 96.5% accuracy, 97.2% TPR and 95.5% TNR with lower overhead. Comparing with others\x92 work, our results increase the accuracy by 4.9%, TPR by 5.6% and TNR by 3.9%. Using our multiple security metrics classification model, though with higher overhead, the detection rate increases to 99.3% accuracy, 99.5% TPR and 99% TNR. Based on our evolution analysis result, we can argue that there can be higher chance to impose update attack, where, the malware is contained in the updated version of a benign application. Our multiple-metrics based classification model is then adapted to detect the update attack and can achieve similar or even better detection rate based on our initial results.

References

This work is mainly done by my student Wenjie Shi for her master thesis.