Deep-Reinforcement-Learning-Based User Profile Perturbation for Privacy-Aware Recommendation

Yilin Xiao, Liang Xiao, Xiaozhen Lu, Hailu Zhang, Shui Yu, H. Vincent Poor

Research output: Contribution to journalArticlepeer-review

43 Scopus citations

Abstract

User profile perturbation protects privacy in the release of user profiles to receive recommendation services, in which the privacy budget as a privacy parameter can be controlled to effect a tradeoff between the recommendation quality and privacy protection against inference attacks. In this article, we propose a deep reinforcement learning (RL)-based user profile perturbation scheme for recommendation systems. This scheme applies differential privacy to protect user privacy and uses deep RL to choose the privacy budget against inference attackers. Based on an evaluated neural network (NN) and a target NN, this scheme enables a user device to optimize the privacy budget over time based on the sensitivity level of the clicked item, the similarities among the recommended items, and the estimated privacy loss. We provide an upper bound on the privacy protection performance of this scheme in the recommendation game and evaluate its computational complexity. Simulation results for a movie recommendation system show that this scheme increases the user privacy protection level for a given recommendation quality compared with benchmark schemes.

Original languageEnglish (US)
Article number9209039
Pages (from-to)4560-4568
Number of pages9
JournalIEEE Internet of Things Journal
Volume8
Issue number6
DOIs
StatePublished - Mar 15 2021
Externally publishedYes

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications

Keywords

  • Inference attacks
  • privacy
  • recommendation systems
  • reinforcement learning (RL)

Fingerprint

Dive into the research topics of 'Deep-Reinforcement-Learning-Based User Profile Perturbation for Privacy-Aware Recommendation'. Together they form a unique fingerprint.

Cite this