Most research on detecting shilling attacks focuses on users' rating behavior but does not consider that attackers may also attack the users' trusting behavior. For example, attackers may give a low score to other users' ratings so that people would think the ratings from the users are not helpful. In this paper, we define the trust shilling attack, propose the behavior features of trust attacks, and present an effective detection method using machine learning methods. The experimental results demonstrate that, based on our proposed behavior features of trust attacks, we can detect trust shilling attacks as well as traditional shilling attacks accurately.
Xian CHEN
Konkuk University
Xi DENG
Chongqing University of Posts and Telecommunications
Chensen HUANG
Chongqing University of Posts and Telecommunications
Hyoseop SHIN
Konkuk University
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Xian CHEN, Xi DENG, Chensen HUANG, Hyoseop SHIN, "Detection of Trust Shilling Attacks in Recommender Systems" in IEICE TRANSACTIONS on Information,
vol. E105-D, no. 6, pp. 1239-1242, June 2022, doi: 10.1587/transinf.2021EDL8094.
Abstract: Most research on detecting shilling attacks focuses on users' rating behavior but does not consider that attackers may also attack the users' trusting behavior. For example, attackers may give a low score to other users' ratings so that people would think the ratings from the users are not helpful. In this paper, we define the trust shilling attack, propose the behavior features of trust attacks, and present an effective detection method using machine learning methods. The experimental results demonstrate that, based on our proposed behavior features of trust attacks, we can detect trust shilling attacks as well as traditional shilling attacks accurately.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2021EDL8094/_p
Copy
@ARTICLE{e105-d_6_1239,
author={Xian CHEN, Xi DENG, Chensen HUANG, Hyoseop SHIN, },
journal={IEICE TRANSACTIONS on Information},
title={Detection of Trust Shilling Attacks in Recommender Systems},
year={2022},
volume={E105-D},
number={6},
pages={1239-1242},
abstract={Most research on detecting shilling attacks focuses on users' rating behavior but does not consider that attackers may also attack the users' trusting behavior. For example, attackers may give a low score to other users' ratings so that people would think the ratings from the users are not helpful. In this paper, we define the trust shilling attack, propose the behavior features of trust attacks, and present an effective detection method using machine learning methods. The experimental results demonstrate that, based on our proposed behavior features of trust attacks, we can detect trust shilling attacks as well as traditional shilling attacks accurately.},
keywords={},
doi={10.1587/transinf.2021EDL8094},
ISSN={1745-1361},
month={June},}
Copy
TY - JOUR
TI - Detection of Trust Shilling Attacks in Recommender Systems
T2 - IEICE TRANSACTIONS on Information
SP - 1239
EP - 1242
AU - Xian CHEN
AU - Xi DENG
AU - Chensen HUANG
AU - Hyoseop SHIN
PY - 2022
DO - 10.1587/transinf.2021EDL8094
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E105-D
IS - 6
JA - IEICE TRANSACTIONS on Information
Y1 - June 2022
AB - Most research on detecting shilling attacks focuses on users' rating behavior but does not consider that attackers may also attack the users' trusting behavior. For example, attackers may give a low score to other users' ratings so that people would think the ratings from the users are not helpful. In this paper, we define the trust shilling attack, propose the behavior features of trust attacks, and present an effective detection method using machine learning methods. The experimental results demonstrate that, based on our proposed behavior features of trust attacks, we can detect trust shilling attacks as well as traditional shilling attacks accurately.
ER -