Exposing Private User Behaviors of Collaborative Filtering via Model Inversion Techniques

Exposing Private User Behaviors of Collaborative Filtering via Model Inversion Techniques

Privacy risks of collaborative filtering (CF) have been widely studied. The current state-of-theart inference attack on user behaviors (e.g., ratings/purchases on sensitive items) for CF is by Calandrino et al. (S&P, 2011). They showed that if an adversary obtained a moderate amount of user’s pu...

Full description

Bibliographic Details
Main Authors: Hidano Seira, Murakami Takao, Katsumata Shuichi, Kiyomoto Shinsaku, Hanaoka Goichiro
Format: Article
Language:English
Published: Sciendo 2020-07-01
Series:Proceedings on Privacy Enhancing Technologies
Subjects:
inference attacks
model inversion attacks
recommender systems
collaborative filtering
data poisoning
privacy exposure
Online Access:https://doi.org/10.2478/popets-2020-0052

Internet

https://doi.org/10.2478/popets-2020-0052

Similar Items