TY - GEN
T1 - Prompt-based Unifying Inference Attack on Graph Neural Networks
AU - Wei, Yuecen
AU - Fu, Xingcheng
AU - Liu, Lingyun
AU - Sun, Qingyun
AU - Peng, Hao
AU - Hu, Chunming
N1 - Publisher Copyright:
Copyright © 2025, Association for the Advancement of Artificial Intelligence (www.aaai.org). All rights reserved.
PY - 2025/4/11
Y1 - 2025/4/11
N2 - Graph neural networks (GNNs) provide important prospective insights in applications such as social behavior analysis and financial risk analysis based on their powerful learning capabilities on graph data. Nevertheless, GNNs' predictive performance relies on the quality of task-specific node labels, so it is common practice to improve the model's generalization ability in the downstream execution of decision-making tasks through pre-training. Graph prompting is a prudent choice but risky without taking measures to prevent data leakage. In other words, in high-risk decision scenarios, prompt learning can infer private information by accessing model parameters trained on private data (publishing model parameters in pre-training, i.e., without directly leaking the raw data, is a tacitly accepted trend). However, myriad graph inference attacks necessitate tailored module design and processing to enhance inference capabilities due to variations in supervision signals. In this paper, we propose a novel Prompt-based unifying Inference Attack framework on GNNs, named ProIA. Specifically, ProIA retains the crucial topological information of the graph during pre-training, enhancing the background knowledge of the inference attack model. It then utilizes a unified prompt and introduces additional disentanglement factors in downstream attacks to adapt to task-relevant knowledge. Finally, extensive experiments show that ProIA enhances attack capabilities and demonstrates remarkable adaptability to various inference attacks.
AB - Graph neural networks (GNNs) provide important prospective insights in applications such as social behavior analysis and financial risk analysis based on their powerful learning capabilities on graph data. Nevertheless, GNNs' predictive performance relies on the quality of task-specific node labels, so it is common practice to improve the model's generalization ability in the downstream execution of decision-making tasks through pre-training. Graph prompting is a prudent choice but risky without taking measures to prevent data leakage. In other words, in high-risk decision scenarios, prompt learning can infer private information by accessing model parameters trained on private data (publishing model parameters in pre-training, i.e., without directly leaking the raw data, is a tacitly accepted trend). However, myriad graph inference attacks necessitate tailored module design and processing to enhance inference capabilities due to variations in supervision signals. In this paper, we propose a novel Prompt-based unifying Inference Attack framework on GNNs, named ProIA. Specifically, ProIA retains the crucial topological information of the graph during pre-training, enhancing the background knowledge of the inference attack model. It then utilizes a unified prompt and introduces additional disentanglement factors in downstream attacks to adapt to task-relevant knowledge. Finally, extensive experiments show that ProIA enhances attack capabilities and demonstrates remarkable adaptability to various inference attacks.
UR - https://www.scopus.com/pages/publications/105003911773
U2 - 10.1609/aaai.v39i12.33400
DO - 10.1609/aaai.v39i12.33400
M3 - 会议稿件
AN - SCOPUS:105003911773
T3 - Proceedings of the AAAI Conference on Artificial Intelligence
SP - 12836
EP - 12844
BT - Special Track on AI Alignment
A2 - Walsh, Toby
A2 - Shah, Julie
A2 - Kolter, Zico
PB - Association for the Advancement of Artificial Intelligence
T2 - 39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025
Y2 - 25 February 2025 through 4 March 2025
ER -