ResearchTrend.AI
  • Papers
  • Communities
  • Events
  • Blog
  • Pricing
Papers
Communities
Social Events
Terms and Conditions
Pricing
Parameter LabParameter LabTwitterGitHubLinkedInBlueskyYoutube

© 2025 ResearchTrend.AI, All rights reserved.

  1. Home
  2. Papers
  3. 2303.14601
13
13

PORE: Provably Robust Recommender Systems against Data Poisoning Attacks

26 March 2023
Jinyuan Jia
Yupei Liu
Yuepeng Hu
Neil Zhenqiang Gong
ArXivPDFHTML
Abstract

Data poisoning attacks spoof a recommender system to make arbitrary, attacker-desired recommendations via injecting fake users with carefully crafted rating scores into the recommender system. We envision a cat-and-mouse game for such data poisoning attacks and their defenses, i.e., new defenses are designed to defend against existing attacks and new attacks are designed to break them. To prevent such a cat-and-mouse game, we propose PORE, the first framework to build provably robust recommender systems in this work. PORE can transform any existing recommender system to be provably robust against any untargeted data poisoning attacks, which aim to reduce the overall performance of a recommender system. Suppose PORE recommends top-NNN items to a user when there is no attack. We prove that PORE still recommends at least rrr of the NNN items to the user under any data poisoning attack, where rrr is a function of the number of fake users in the attack. Moreover, we design an efficient algorithm to compute rrr for each user. We empirically evaluate PORE on popular benchmark datasets.

View on arXiv
Comments on this paper