ePrints@IIScePrints@IISc Home | About | Browse | Latest Additions | Advanced Search | Contact | Help

Data Poisoning Attacks against Differentially Private Recommender Systems

Wadhwa, S and Agrawal, S and Chaudhari, H and Sharma, D and Achan, K (2020) Data Poisoning Attacks against Differentially Private Recommender Systems. In: 43rd Annual International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2020, 25-30 July 2020, China, pp. 1617-1620.

sig_pro_int_acm_sig_con_res_dev_inf_ret_1617-1620_2020.pdf - Published Version

Download (1MB) | Preview
Official URL: https://dx.doi.org/10.1145/3397271.3401301


Recommender systems based on collaborative filtering are highly vulnerable to data poisoning attacks, where a determined attacker injects fake users with false user-item feedback, with an objective to either corrupt the recommender system or promote/demote a target set of items. Recently, differential privacy was explored as a defense technique against data poisoning attacks in the typical machine learning setting. In this paper, we study the effectiveness of differential privacy against such attacks on matrix factorization based collaborative filtering systems. Concretely, we conduct extensive experiments for evaluating robustness to injection of malicious user profiles by simulating common types of shilling attacks on real-world data and comparing the predictions of typical matrix factorization with differentially private matrix factorization. © 2020 ACM.

Item Type: Conference Paper
Additional Information: The copyright of this article belongs to Association for Computing Machinery, Inc
Keywords: Collaborative filtering; Factorization; Recommender systems, Collaborative filtering systems; Defense techniques; Differential privacies; Matrix factorizations; Poisoning attacks; Real-world; User profile, Matrix algebra
Department/Centre: Division of Electrical Sciences > Computer Science & Automation
Depositing User: Bharath k v
Date Deposited: 28 Sep 2020 06:52
Last Modified: 28 Sep 2020 06:52
URI: http://eprints.iisc.ac.in/id/eprint/66536

Actions (login required)

View Item View Item