RecPS: Privacy Risk Scoring for Recommender Systems

• URL: http://arxiv.org/abs/2507.18365v3
• Date: Fri, 01 Aug 2025 17:19:56 GMT
• Title: RecPS: Privacy Risk Scoring for Recommender Systems
• Authors: Jiajie He, Yuechun Gu, Keke Chen,
• Abstract summary: We propose a membership-inference attack (MIA)-based privacy scoring method, RecPS, to measure privacy risks at both the interaction and user levels.<n>A critical component is the interaction-level MIA method RecLiRA, which gives high-quality membership estimation.
• Score: 4.772368796656325
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Recommender systems (RecSys) have become an essential component of many web applications. The core of the system is a recommendation model trained on highly sensitive user-item interaction data. While privacy-enhancing techniques are actively studied in the research community, the real-world model development still depends on minimal privacy protection, e.g., via controlled access. Users of such systems should have the right to choose \emph{not} to share highly sensitive interactions. However, there is no method allowing the user to know which interactions are more sensitive than others. Thus, quantifying the privacy risk of RecSys training data is a critical step to enabling privacy-aware RecSys model development and deployment. We propose a membership-inference attack (MIA)- based privacy scoring method, RecPS, to measure privacy risks at both the interaction and user levels. The RecPS interaction-level score definition is motivated and derived from differential privacy, which is then extended to the user-level scoring method. A critical component is the interaction-level MIA method RecLiRA, which gives high-quality membership estimation. We have conducted extensive experiments on well-known benchmark datasets and RecSys models to show the unique features and benefits of RecPS scoring in risk assessment and RecSys model unlearning.

Related papers

• Churn-Aware Recommendation Planning under Aggregated Preference Feedback [6.261444979025644]
  We study a sequential decision-making problem motivated by recent regulatory and technological shifts.<n>We introduce the Rec-APC model, in which an anonymous user is drawn from a known prior over latent user types.<n>We prove that optimal policies converge to pure exploitation in finite time and propose a branch-and-bound algorithm to efficiently compute them.
  arXiv  Detail & Related papers  (2025-07-06T19:22:47Z)
• Multi-agents based User Values Mining for Recommendation [52.26100802380767]
  We propose a zero-shot multi-LLM collaborative framework for effective and accurate user value extraction.<n>We apply text summarization techniques to condense item content while preserving essential meaning.<n>To mitigate hallucinations, we introduce two specialized agent roles: evaluators and supervisors.
  arXiv  Detail & Related papers  (2025-05-02T04:01:31Z)
• Search-Based Interaction For Conversation Recommendation via Generative Reward Model Based Simulated User [117.82681846559909]
  Conversational recommendation systems (CRSs) use multi-turn interaction to capture user preferences and provide personalized recommendations.<n>We propose a generative reward model based simulated user, named GRSU, for automatic interaction with CRSs.
  arXiv  Detail & Related papers  (2025-04-29T06:37:30Z)
• Mind the Privacy Unit! User-Level Differential Privacy for Language Model Fine-Tuning [62.224804688233]
  differential privacy (DP) offers a promising solution by ensuring models are 'almost indistinguishable' with or without any particular privacy unit. We study user-level DP motivated by applications where it necessary to ensure uniform privacy protection across users.
  arXiv  Detail & Related papers  (2024-06-20T13:54:32Z)
• FedRKG: A Privacy-preserving Federated Recommendation Framework via Knowledge Graph Enhancement [20.214339212091012]
  Federated Learning (FL) has emerged as a promising approach for preserving data privacy in recommendation systems by training models locally. Recent Graph Neural Networks (GNN) have gained popularity in recommendation tasks due to their ability to capture high-order interactions between users and items. We propose FedRKG, a novel federated recommendation system, where a global knowledge graph (KG) is constructed and maintained on the server using publicly available item information.
  arXiv  Detail & Related papers  (2024-01-20T02:38:21Z)
• On Generative Agents in Recommendation [58.42840923200071]
  Agent4Rec is a user simulator in recommendation based on Large Language Models. Each agent interacts with personalized recommender models in a page-by-page manner.
  arXiv  Detail & Related papers  (2023-10-16T06:41:16Z)
• Inferring Communities of Interest in Collaborative Learning-based Recommender Systems [1.9093042949944972]
  Collaborative-learning-based recommender systems allow users to train models while keeping their history of liked items on their devices.<n>Recent research has shown that collaborative learning can be vulnerable to various privacy attacks.<n>We propose a novel attack called Community Inference Attack (CIA), which enables an adversary to identify community members based on a set of target items.
  arXiv  Detail & Related papers  (2023-06-15T08:02:07Z)
• Multi-View Interactive Collaborative Filtering [0.0]
  We propose a novel partially online latent factor recommender algorithm that incorporates both rating and contextual information. MV-ICTR significantly increases performance on datasets with high percentages of cold-start users and items.
  arXiv  Detail & Related papers  (2023-05-14T20:31:37Z)
• Unlearning Protected User Attributes in Recommendations with Adversarial Training [10.268369743620159]
  Collaborative filtering algorithms capture underlying consumption patterns, including the ones specific to particular demographics or protected information of users. These encoded biases can influence the decision of a recommendation system towards further separation of the contents provided to various demographic subgroups. In this work, we investigate the possibility and challenges of removing specific protected information of users from the learned interaction representations of a RS algorithm.
  arXiv  Detail & Related papers  (2022-06-09T13:36:28Z)
• Towards Automatic Evaluation of Dialog Systems: A Model-Free Off-Policy Evaluation Approach [84.02388020258141]
  We propose a new framework named ENIGMA for estimating human evaluation scores based on off-policy evaluation in reinforcement learning. ENIGMA only requires a handful of pre-collected experience data, and therefore does not involve human interaction with the target policy during the evaluation. Our experiments show that ENIGMA significantly outperforms existing methods in terms of correlation with human evaluation scores.
  arXiv  Detail & Related papers  (2021-02-20T03:29:20Z)
• Seamlessly Unifying Attributes and Items: Conversational Recommendation for Cold-Start Users [111.28351584726092]
  We consider the conversational recommendation for cold-start users, where a system can both ask the attributes from and recommend items to a user interactively. Our Conversational Thompson Sampling (ConTS) model holistically solves all questions in conversational recommendation by choosing the arm with the maximal reward to play.
  arXiv  Detail & Related papers  (2020-05-23T08:56:37Z)
• Systematic Evaluation of Privacy Risks of Machine Learning Models [41.017707772150835]
  We show that prior work on membership inference attacks may severely underestimate the privacy risks. We first propose to benchmark membership inference privacy risks by improving existing non-neural network based inference attacks. We then introduce a new approach for fine-grained privacy analysis by formulating and deriving a new metric called the privacy risk score.
  arXiv  Detail & Related papers  (2020-03-24T00:53:53Z)
• Federating Recommendations Using Differentially Private Prototypes [16.29544153550663]
  We propose a new federated approach to learning global and local private models for recommendation without collecting raw data. By requiring only two rounds of communication, we both reduce the communication costs and avoid the excessive privacy loss. We show local adaptation of the global model allows our method to outperform centralized matrix-factorization-based recommender system models.
  arXiv  Detail & Related papers  (2020-03-01T22:21:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.