Yuanxin Zhuang, Chuan Shi, and Mengmei Zhang, Beijing University of Posts and Telecommunications; Jinghui Chen, The Pennsylvania State University; Lingjuan Lyu, SONY AI; Pan Zhou, Huazhong University of Science and Technology; Lichao Sun, Lehigh University
Graph neural networks (GNNs) play a crucial role in various graph applications, such as social science, biology, and molecular chemistry. Despite their popularity, GNNs are still vulnerable to intellectual property threats. Previous studies have demonstrated the susceptibility of GNN models to model extraction attacks, where attackers steal the functionality of GNNs by sending queries and obtaining model responses. However, existing model extraction attacks often assume that the attacker has access to specific information about the victim model's training data, including node attributes, connections, and the shadow dataset. This assumption is impractical in real-world scenarios. To address this issue, we propose StealGNN, the first data-free model extraction attack framework against GNNs. StealGNN advances prior GNN extraction attacks in three key aspects: 1) It is completely data-free, as it does not require actual node features or graph structures to extract GNN models. 2) It constitutes a full-rank attack that can be applied to node classification and link prediction tasks, posing significant intellectual property threats across a wide range of graph applications. 3) It can handle the most challenging hard-label attack setting, where the attacker possesses no knowledge about the target GNN model and can only obtain predicted labels through querying the victim model. Our experimental results on four benchmark graph datasets demonstrate the effectiveness of StealGNN in attacking representative GNN models.
Open Access Media
USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.
author = {Yuanxin Zhuang and Chuan Shi and Mengmei Zhang and Jinghui Chen and Lingjuan Lyu and Pan Zhou and Lichao Sun},
title = {Unveiling the Secrets without Data: Can Graph Neural Networks Be Exploited through {Data-Free} Model Extraction Attacks?},
booktitle = {33rd USENIX Security Symposium (USENIX Security 24)},
year = {2024},
isbn = {978-1-939133-44-1},
address = {Philadelphia, PA},
pages = {5251--5268},
url = {https://www.usenix.org/conference/usenixsecurity24/presentation/zhuang},
publisher = {USENIX Association},
month = aug
}