TY - GEN
T1 - A Review of Poisoning Attacks on Graph Neural Networks
AU - Seol, Kihyun
AU - Lee, Yerin
AU - Song, Seungyeop
AU - Park, Heejae
AU - Park, Laihyuk
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - A Graph Neural Network (GNN) is designed to generate effective node embeddings in graph-structured data. Therefore, GNNs are well-suited for tasks like node classification and graph generation. As their use has expanded, concerns about their security, robustness, and privacy have grown. This paper explores the various adversarial attacks that can be executed against G NN s, focusing on poisoning attacks, a specific type of adversarial attack. We examine key attack strategies and review recent research developments in each attack. Finally, we conclude with proposals aimed at enhancing the robustness of GNNs.
AB - A Graph Neural Network (GNN) is designed to generate effective node embeddings in graph-structured data. Therefore, GNNs are well-suited for tasks like node classification and graph generation. As their use has expanded, concerns about their security, robustness, and privacy have grown. This paper explores the various adversarial attacks that can be executed against G NN s, focusing on poisoning attacks, a specific type of adversarial attack. We examine key attack strategies and review recent research developments in each attack. Finally, we conclude with proposals aimed at enhancing the robustness of GNNs.
KW - Adversarial attack
KW - GNNs
KW - poisoning attack
UR - https://www.scopus.com/pages/publications/85217706769
U2 - 10.1109/ICTC62082.2024.10827707
DO - 10.1109/ICTC62082.2024.10827707
M3 - Conference contribution
AN - SCOPUS:85217706769
T3 - International Conference on ICT Convergence
SP - 239
EP - 240
BT - ICTC 2024 - 15th International Conference on ICT Convergence
PB - IEEE Computer Society
T2 - 15th International Conference on Information and Communication Technology Convergence, ICTC 2024
Y2 - 16 October 2024 through 18 October 2024
ER -