Lune

EMNLP Findings2020

PrivNet: Safeguarding Private Attributes in Transfer Learning for Recommendation

Guangneng Hu, Qiang Yang

Abstract

Transfer learning is an effective technique to improve a target recommender system with the knowledge from a source domain. Existing research focuses on the recommendation performance of the target domain while ignores the privacy leakage of the source domain. The transferred knowledge, however, may unintendedly leak private information of the source domain. For example, an attacker can accurately infer user demographics from their historical purchase provided by a source domain data owner. This paper addresses the above privacy-preserving issue by learning a privacyaware neural representation by improving target performance while protecting source privacy. The key idea is to simulate the attacks during the training for protecting unseen users' privacy in the future, modeled by an adversarial game, so that the transfer learning model becomes robust to attacks. Experiments show that the proposed PrivNet model can successfully disentangle the knowledge benefitting the transfer from leaking the privacy.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

Builds onCited byLeft to right by year; the more cited, the higher.

Builds on3

  1. AttriGuard: A Practical Defense Against Attribute Inference Attacks via Adversarial Machine LearningJinyuan Jia, Neil Zhenqiang GongUSENIX Security 2018 · 194 citations
  2. Null It Out: Guarding Protected Attributes by Iterative Nullspace ProjectionShauli Ravfogel, Yanai Elazar, Hila Gonen, Michael Twiton et al.ACL 2020 · 25 citations
  3. Differentially Private Learning with Small Public DataJun Wang, Zhi-Hua ZhouAAAI 2020 · 25 citations

Related papers

  1. PPGenCDR: A Stable and Robust Framework for Privacy-Preserving Cross-Domain RecommendationXinting Liao, Weiming Liu, Xiaolin Zheng, Binhui Yao et al.AAAI 2023 · 28 citations
  2. Reducing Item Discrepancy via Differentially Private Robust Embedding Alignment for Privacy-Preserving Cross Domain RecommendationWeiming Liu, Xiaolin Zheng, Chaochao Chen, Jiahe Xu et al.ICML 2024 · 5 citations
  3. Differential Private Knowledge Transfer for Privacy-Preserving Cross-Domain RecommendationChaochao Chen, Huiwen Wu, Jiajie Su, Lingjuan Lyu et al.WWW 2022 · 95 citations
  4. Differentially Private Representation for NLP: Formal Guarantee and An Empirical Study on Privacy and FairnessLingjuan Lyu, Xuanli He, Yitong LiEMNLP Findings 2020 · 51 citations
  5. Federated Graph Learning for Cross-Domain RecommendationZiqi Yang, Zhaopeng Peng, Zihui Wang, Jianzhong Qi et al.NeurIPS 2024 · 24 citations
Dusk over the sea between two cliffs drawn in fine vertical lines