Practical Cross-System Shilling Attacks with Limited Access to Data
Proceedings of the AAAI Conference on Artificial Intelligence · 26.06.2023 · 37 (4) · 4864-4874
DOI: 10.1609/aaai.v37i4.25612 ↗Kurz gefasst
Fachartikel in der Zeitschrift Proceedings of the AAAI Conference on Artificial Intelligence, online erschienen am 26.06.2023. Verfasst von Meifang Zeng und 4 weiteren Autor:innen. Die Arbeit wurde bisher 8-mal zitiert (Crossref).
Abstract (Originalsprache)
In shilling attacks, an adversarial party injects a few fake user profiles into a Recommender System (RS) so that the target item can be promoted or demoted. Although much effort has been devoted to developing shilling attack methods, we find that existing approaches are still far from practical. In this paper, we analyze the properties a practical shilling attack method should have and propose a new concept of Cross-system Attack. With the idea of Cross-system Attack, we design a Practical Cross-system Shilling Attack (PC-Attack) framework that requires little information about the victim RS model and the target RS data for conducting attacks. PC-Attack is trained to capture graph topology knowledge from public RS data in a self-supervised manner. Then, it is fine-tuned on a small portion of target data that is easy to access to construct fake profiles. Extensive experiments have demonstrated the superiority of PC-Attack over state-of-the-art baselines. Our implementation of PC-Attack is available at https://github.com/KDEGroup/PC-Attack.
Zitieren
APA
Zeng, M., Li, K., Jiang, B., Cao, L., & Li, H. (2023). Practical Cross-System Shilling Attacks with Limited Access to Data. Proceedings of the AAAI Conference on Artificial Intelligence, 37(4), 4864-4874. https://doi.org/10.1609/aaai.v37i4.25612
Vancouver
Zeng M, Li K, Jiang B, Cao L, Li H. Practical Cross-System Shilling Attacks with Limited Access to Data. Proceedings of the AAAI Conference on Artificial Intelligence. 2023;37(4):4864-4874. doi:10.1609/aaai.v37i4.25612
BibTeX
@article{Zeng2023,
author = {Zeng, Meifang and Li, Ke and Jiang, Bingchuan and Cao, Liujuan and Li, Hui},
title = {Practical Cross-System Shilling Attacks with Limited Access to Data},
journal = {Proceedings of the AAAI Conference on Artificial Intelligence},
year = {2023},
volume = {37},
number = {4},
pages = {4864--4874},
doi = {10.1609/aaai.v37i4.25612}
}
EUVIMED