DeepCatra: Learning Flow- and Graph-based Behaviors for Android Malware Detection

TL;DR

DeepCatra introduces a multi-view deep learning model combining BiLSTM and GNN to improve Android malware detection accuracy by leveraging call trace and flow graph features from static analysis.

Contribution

The paper presents DeepCatra, a novel multi-view learning approach integrating BiLSTM and GNN for enhanced Android malware detection using static call graph features.

Findings

Achieves 2.7% to 14.6% improvement in F1-measure over state-of-the-art methods

Effective in detecting malware in over 18,000 real-world apps

Demonstrates practical feasibility of multi-view deep learning for malware detection

Abstract

As Android malware is growing and evolving, deep learning has been introduced into malware detection, resulting in great effectiveness. Recent work is considering hybrid models and multi-view learning. However, they use only simple features, limiting the accuracy of these approaches in practice. In this paper, we propose DeepCatra, a multi-view learning approach for Android malware detection, whose model consists of a bidirectional LSTM (BiLSTM) and a graph neural network (GNN) as subnets. The two subnets rely on features extracted from statically computed call traces leading to critical APIs derived from public vulnerabilities. For each Android app, DeepCatra first constructs its call graph and computes call traces reaching critical APIs. Then, temporal opcode features used by the BiLSTM subnet are extracted from the call traces, while flow graph features used by the GNN subnet are constructed from all the call traces and inter-component communications. We evaluate the effectiveness of DeepCatra by comparing it with several state-of-the-art detection approaches. Experimental results on over 18,000 real-world apps and prevalent malware show that DeepCatra achieves considerable improvement, e.g., 2.7% to 14.6% on F1-measure, which demonstrates the feasibility of DeepCatra in practice.