Adversarial Attacks for Black-Box Recommender Systems via Copying Transferable Cross-Domain User Profiles
IEEE Transactions on Knowledge and Data Engineering · 01.12.2023 · 35 (12) · 12415-12429
DOI: 10.1109/tkde.2023.3272652 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Knowledge and Data Engineering, erschienen am 01.12.2023. Verfasst von Wenqi Fan und 7 weiteren Autor:innen. Die Arbeit wurde bisher 45-mal zitiert (Crossref) und nennt 59 Literaturangaben. Gefördert von: National Natural Science Foundation of China, General Research Funds from the Hong Kong Research Grants Council, Hong Kong Polytechnic University.
Abstract (Originalsprache)
As widely used in data-driven decision-making, recommender systems have been recognized for their capabilities to provide users with personalized services in many user-oriented online services, such as E-commerce (e.g., Amazon, Taobao, etc.) and Social Media sites (e.g., Facebook and Twitter). Recent works have shown that deep neural networks-based recommender systems are highly vulnerable to adversarial attacks, where adversaries can inject carefully crafted fake user profiles (i.e., a set of items that fake users have interacted with) into a target recommender system to promote or demote a set of target items. Instead of generating users with fake profiles from scratch, in this article, we introduce a novel strategy to obtain “fake” user profiles via copying cross-domain user profiles, where a reinforcement learning based black-box attacking framework (CopyAttack+) is developed to effectively and efficiently select cross-domain user profiles from the source domain to attack the target system. Moreover, we propose to train a local surrogate system for mimicking adversarial black-box attacks in the source domain, so as to provide transferable signals with the purpose of enhancing the attacking strategy in the target black-box recommender system. Comprehensive experiments on three real-world datasets are conducted to demonstrate the effectiveness of the proposed attacking framework.
Förderung
- National Natural Science Foundation of China
- General Research Funds from the Hong Kong Research Grants Council
- Hong Kong Polytechnic University
- Research Collaborative
- SHTM Interdisciplinary Large
- Hong Kong Research Grant Council
- APRC-CityU New Research Initiatives
- New Faculty of City University of Hong Kong
Zitieren
APA
Fan, W., Zhao, X., Li, Q., Derr, T., Ma, Y., Liu, H., Wang, J., & Tang, J. (2023). Adversarial Attacks for Black-Box Recommender Systems via Copying Transferable Cross-Domain User Profiles. IEEE Transactions on Knowledge and Data Engineering, 35(12), 12415-12429. https://doi.org/10.1109/tkde.2023.3272652
Vancouver
Fan W, Zhao X, Li Q, Derr T, Ma Y, Liu H, et al. Adversarial Attacks for Black-Box Recommender Systems via Copying Transferable Cross-Domain User Profiles. IEEE Transactions on Knowledge and Data Engineering. 2023;35(12):12415-12429. doi:10.1109/tkde.2023.3272652
BibTeX
@article{Fan2023,
author = {Fan, Wenqi and Zhao, Xiangyu and Li, Qing and Derr, Tyler and Ma, Yao and Liu, Hui and Wang, Jianping and Tang, Jiliang},
title = {Adversarial Attacks for Black-Box Recommender Systems via Copying Transferable Cross-Domain User Profiles},
journal = {IEEE Transactions on Knowledge and Data Engineering},
year = {2023},
volume = {35},
number = {12},
pages = {12415--12429},
doi = {10.1109/tkde.2023.3272652}
}
EUVIMED