Influence-Driven Data Poisoning for Robust Recommender Systems

Recent studies have shown that recommender systems are vulnerable, and it is easy for attackers to inject well-designed malicious profiles into the system, resulting in biased recommendations. We cannot deprive these data's injection right and deny their existence's rationality, making it...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	IEEE transactions on pattern analysis and machine intelligence 2023-10, Vol.45 (10), p.11915-11931
Hauptverfasser:	Wu, Chenwang, Lian, Defu, Ge, Yong, Zhu, Zhihao, Chen, Enhong
Format:	Artikel
Sprache:	eng
Schlagworte:	Adversarial training Data models Empirical analysis Generators Influence functions Optimization Perturbation methods poisoning attacks Recommender systems Robustness Strategy Training
Online-Zugang:	Volltext bestellen
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!