<ul><li>This paper introduces a novel Prompt-based unifying Inference Attack framework on Graph Neural Networks (GNNs), named ProIA.</li><li>ProIA retains the graph's topological information during pre-training, enhancing the background knowledge of the inference attack model.</li><li>It utilizes a unified prompt and introduces additional disentanglement factors in downstream attacks to adapt to task-relevant knowledge.</li><li>Extensive experiments show that ProIA enhances attack capabilities and demonstrates remarkable adaptability to various inference attacks.</li></ul>

Prompt-based Unifying Inference Attack on Graph Neural Networks

Discover more