6Graph Convolutional Network for Detection
Graph Convolutional Network (GCN) is a graph representation learning approach that represents the structure and features of the graph in a low dimensional Euclidean space. GCN has found to give promising results in many real-world applications such as learning social networks[206], traffic prediction[220], drug response prediction [156], etc. as well as in Android malware detection [128]. In this chapter, we discuss the application GCN in Android malware detection and illustrate with the detection of obfuscated Android malware from system call graphs. We organised the chapter as follows. Section 6.2 gives an introduction of GCN and its applications in many real-world problems, ...
Get Intelligent Mobile Malware Detection now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
