Due to its open-source nature, Android operating system has been the main target of attackers to exploit. Malware creators always perform different code obfuscations on their apps to hide malicious activities. Features extracted from these obfuscated samples through program analysis contain many useless and disguised features, which leads to many false negatives. To address the issue, in this paper, we demonstrate that obfuscation-resilient malware analysis can be achieved through contrastive learning. We take the Android malware classification as an example to demonstrate our analysis. The key insight behind our analysis is that contrastive learning can be used to reduce the difference introduced by obfuscation while amplifying the difference between malware and benign apps (or other types of malware). Based on the proposed analysis, we design a system that can achieve robust and interpretable classification of Android malware. To achieve robust classification, we perform contrastive learning on malware samples to learn an encoder that can automatically extract robust features from malware samples. To achieve interpretable classification, we transform the function call graph of a sample into an image by centrality analysis. Then the corresponding heatmaps are obtained by visualization techniques. These heatmaps can help users understand why the malware is classified as this family. We implement IFDroid and perform extensive evaluations on two widely used datasets. Experimental results show that IFDroid is superior to state-of-the-art Android malware familial classification systems. Moreover, IFDroid is capable of maintaining 98.2% true positive rate on classifying 8,112 obfuscated malware samples.
Download