EUVIMEDEUVIMED entdecken
Crossref

Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs

Dongjin Lee, Juho Lee, Kijung Shin

Proceedings of the AAAI Conference on Artificial Intelligence · 24.03.2024 · 38 (12) · 13374-13382

DOI: 10.1609/aaai.v38i12.29239 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 24.03.2024. Verfasst von Dongjin Lee und 2 weiteren Autor:innen. Die Arbeit wurde bisher 10-mal zitiert (Crossref).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Real-world graphs are dynamic, constantly evolving with new interactions, such as financial transactions in financial networks. Temporal Graph Neural Networks (TGNNs) have been developed to effectively capture the evolving patterns in dynamic graphs. While these models have demonstrated their superiority, being widely adopted in various important fields, their vulnerabilities against adversarial attacks remain largely unexplored. In this paper, we propose T-SPEAR, a simple and effective adversarial attack method for link prediction on continuous-time dynamic graphs, focusing on investigating the vulnerabilities of TGNNs. Specifically, before the training procedure of a victim model, which is a TGNN for link prediction, we inject edge perturbations to the data that are unnoticeable in terms of the four constraints we propose, and yet effective enough to cause malfunction of the victim model. Moreover, we propose a robust training approach T-SHIELD to mitigate the impact of adversarial attacks. By using edge filtering and enforcing temporal smoothness to node embeddings, we enhance the robustness of the victim model. Our experimental study shows that T-SPEAR significantly degrades the victim model's performance on link prediction tasks, and even more, our attacks are transferable to other TGNNs, which differ from the victim model assumed by the attacker. Moreover, we demonstrate that T-SHIELD effectively filters out adversarial edges and exhibits robustness against adversarial attacks, surpassing the link prediction performance of the naive TGNN by up to 11.2% under T-SPEAR. The code and datasets are available at https://github.com/wooner49/T-spear-shield

Zitieren

APA

Lee, D., Lee, J., & Shin, K. (2024). Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs. Proceedings of the AAAI Conference on Artificial Intelligence, 38(12), 13374-13382. https://doi.org/10.1609/aaai.v38i12.29239

Vancouver

Lee D, Lee J, Shin K. Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs. Proceedings of the AAAI Conference on Artificial Intelligence. 2024;38(12):13374-13382. doi:10.1609/aaai.v38i12.29239

BibTeX
@article{Lee2024,
  author = {Lee, Dongjin and Lee, Juho and Shin, Kijung},
  title = {Spear and Shield: Adversarial Attacks and Defense Methods for Model-Based Link Prediction on Continuous-Time Dynamic Graphs},
  journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
  year = {2024},
  volume = {38},
  number = {12},
  pages = {13374--13382},
  doi = {10.1609/aaai.v38i12.29239}
}
Kostenlos starten →