Recommender Systems Robust to Data Poisoning using Trim Learning

Seira Hidano, Shinsaku Kiyomoto

2020

Abstract

Recommender systems have been widely utilized in various e-commerce systems for improving user experience. However, since security threats, such as fake reviews and fake ratings, are becoming apparent, users are beginning to have their doubts about trust of such systems. The data poisoning attack is one of representative attacks for recommender systems. While acting as a legitimate user on the system, the adversary attempts to manipulate recommended items using fake ratings. Although several defense methods also have been proposed, most of them require prior knowledge on real and/or fake ratings. We thus propose recommender systems robust to data poisoning without any knowledge.

Paper Citation

in Harvard Style

Hidano S. and Kiyomoto S. (2020). Recommender Systems Robust to Data Poisoning using Trim Learning. In Proceedings of the 6th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP, ISBN 978-989-758-399-5, pages 721-724. DOI: 10.5220/0009180407210724

in Bibtex Style

@conference{icissp20,
author={Seira Hidano and Shinsaku Kiyomoto},
title={Recommender Systems Robust to Data Poisoning using Trim Learning},
booktitle={Proceedings of the 6th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,},
year={2020},
pages={721-724},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0009180407210724},
isbn={978-989-758-399-5},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 6th International Conference on Information Systems Security and Privacy - Volume 1: ICISSP,
TI - Recommender Systems Robust to Data Poisoning using Trim Learning
SN - 978-989-758-399-5
AU - Hidano S.
AU - Kiyomoto S.
PY - 2020
SP - 721
EP - 724
DO - 10.5220/0009180407210724