TY - GEN
T1 - Adversarial attacks on node embeddings via graph poisoning
AU - Bojchevski, Aleksandar
AU - Günnemann, Stephan
N1 - Publisher Copyright:
© 36th International Conference on Machine Learning, ICML 2019. All rights reserved.
PY - 2019
Y1 - 2019
N2 - The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no study of their robustness to adversarial attacks. We provide the first adversarial vulnerability analysis on the widely used family of methods based on random walks. We derive efficient adversarial perturbations that poison the network structure and have a negative effect on both the quality of the embeddings and the downstream tasks. We further show that our attacks are transferable since they generalize to many models and are successful even when the attacker is restricted.
AB - The goal of network representation learning is to learn low-dimensional node embeddings that capture the graph structure and are useful for solving downstream tasks. However, despite the proliferation of such methods, there is currently no study of their robustness to adversarial attacks. We provide the first adversarial vulnerability analysis on the widely used family of methods based on random walks. We derive efficient adversarial perturbations that poison the network structure and have a negative effect on both the quality of the embeddings and the downstream tasks. We further show that our attacks are transferable since they generalize to many models and are successful even when the attacker is restricted.
UR - http://www.scopus.com/inward/record.url?scp=85071150199&partnerID=8YFLogxK
M3 - Conference contribution
AN - SCOPUS:85071150199
T3 - 36th International Conference on Machine Learning, ICML 2019
SP - 1112
EP - 1123
BT - 36th International Conference on Machine Learning, ICML 2019
PB - International Machine Learning Society (IMLS)
T2 - 36th International Conference on Machine Learning, ICML 2019
Y2 - 9 June 2019 through 15 June 2019
ER -