Enyan Dai

Enyan Dai

HKUST(GZ), Assistant Professor @ AI Thrust

[Video] Introduction about Unnoticeable Backdoor Attacks on Graph Neural Networks (WWW-2023)

less than 1 minute read

Published:

Summary: we study a novel problem of unnoticeable graph backdoor attacks with limited attack budget. The proposed method can achieve high attack rate on large-scale datasets with samll costs.

Papaer link: Enyan Dai, Minhua Lin, Xiang Zhang, and Suhang Wang. “Unnoticeable Backdoor Attacks on Graph Neural Networks” Accepted by The Web Conference (WWW 2023) [paper, code]

English

中文加长版

You May Also Enjoy

[Video] Introduction about robust structural noise-resistant GNN (WSDM-2022)

less than 1 minute read

Published:

Summary: we study a novel problem of developing robust GNNs on noisy graphs with limited labeled nodes. We propose to learn a denoised and dense graph, which can down-weight or eliminate noisy edges and facilitate message passing of GNNs to alleviate the issue of limited labeled nodes.