Membership Inference Attacks on Recommender System: A Survey
cs.IR, cs.AI, cs.CR
Submitted: 2025-09-14
Updated: 2026-09-11
Comments: under review in ACM TOIS
Code: https://github.com/Richardwarriors/Membership-Inference-Attacks-on-Recommendation-System
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Terminology
Sources
- Machine Unlearning
- Knowledge Graph Completion Models are Few-shot Learners: An Empirical Study of Relation Labeling in E-commerce with LLMs
- Shadow-Free Membership Inference Attacks: Recommender Systems Are More Vulnerable Than You Thought
- M6-Rec: Generative Pretrained Language Models are Open-Ended Recommender Systems
- Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
- Auditing Approximate Machine Unlearning for Differentially Private Models
- Membership Inference Attacks on In-Context Examples in LLM-based Recommender Systems
- Session-based Recommendations with Recurrent Neural Networks
- Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders
- Making Recommender Systems Forget: Learning and Unlearning for Erasable Recommendation
- Forgetting Fast in Recommender Systems
- Membership Inference Attacks by Exploiting Loss Trajectory
- SimpleX: A Simple and Strong Baseline for Collaborative Filtering
- Learning Differentially Private Recurrent Language Models
- A Survey of Machine Unlearning
- BPR: Bayesian Personalized Ranking from Implicit Feedback
- Federated Collaborative Filtering for Privacy-Preserving Personalized Recommendation System
- Fast-adapting and Privacy-preserving Federated Recommender System
- Membership Inference Attacks Against In-Context Learning
- Comprehensive Privacy Analysis on Federated Recommender System against Attribute Inference Attacks
Related papers
- The Price of Isolation: Estimating the Ecosystem Cost of Symmetric Two-Sided A/B Testing
- SCAR: Semantic Continuity-Aware Retrieval for Efficient Context Expansion in RAG
- MixLoRA-DSI: Dynamically Expandable Mixture-of-LoRA Experts for Rehearsal-Free Generative Retrieval over Dynamic Corpora
- RRCM: Ranking-Driven Retrieval over Collaborative and Meta Memories for LLM Recommendation
- Right Family, Wrong Skill: Evaluating Risk Exposure in Agent Skill Retrieval
- UltRAG: a Universal Simple Scalable Recipe for Knowledge Graph RAG