VertexSerum: Poisoning Graph Neural Networks for Link Inference. (arXiv:2308.01469v1 [cs.LG])

Graph neural networks (GNNs) have brought superb performance to various
applications utilizing graph structural data, such as social analysis and fraud
detection. The graph links, e.g., social relationships and transaction history,
are sensitive and valuable information, which raises privacy concerns when
using GNNs. To exploit these vulnerabilities, we propose VertexSerum, a novel
graph poisoning attack that increases the effectiveness of graph link stealing
by amplifying the link connectivity leakage. To infer node adjacency more
accurately, we propose an attention mechanism …

analysis applications data detection exploit fraud fraud detection history information link links networks neural networks performance poisoning privacy privacy concerns relationships social transaction vulnerabilities