Accurate mobile-app fingerprinting using flow-level relationship with graph neural networks

learning, and we designed a powerful GNN-based traffic fingerprint learner. We conduct comprehensive experiments on both public and private datasets. The results show the FG-Net outperforms the SOTAs in classifying traffic with about 18% common traffic. Without retraining, FG-Net obtains the most robustness against the updated traffic and increases the accuracy by 5.5% compared with the SOTAs.