# Preserving Privacy and Utility in LLM-Based Product Recommendations

arXiv: https://arxiv.org/abs/2505.00951 · HTML: https://mlsanity.com/paper/2505.00951/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 20 of its 52 references that are in the map.
- First posted on arXiv 2 May 2025.

## Builds on (most cited first, 20 of 20)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Neural Collaborative Filtering](https://mlsanity.com/paper/1708.05031/) (2017)
- [How to Fine-Tune BERT for Text Classification?](https://mlsanity.com/paper/1905.05583/) (2019)
- [A Survey on Large Language Models for Recommendation](https://mlsanity.com/paper/2305.19860/) (2023)
- [Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System](https://mlsanity.com/paper/2303.14524/) (2023)
- [Bridging Language and Items for Retrieval and Recommendation: Benchmarking LLMs as Semantic Encoders](https://mlsanity.com/paper/2403.03952/) (2024)
- [Security and Privacy Challenges of Large Language Models: A Survey](https://mlsanity.com/paper/2402.00888/) (2024)
- [Is Cosine-Similarity of Embeddings Really About Similarity?](https://mlsanity.com/paper/2403.05440/) (2024)
- [THE-X: Privacy-Preserving Transformer Inference with Homomorphic Encryption](https://mlsanity.com/paper/2206.00216/) (2022)
- [A Large Language Model Enhanced Conversational Recommender System](https://mlsanity.com/paper/2308.06212/) (2023)
- [Evaluating ChatGPT as a Recommender System: A Rigorous Approach](https://mlsanity.com/paper/2309.03613/) (2023)
- [Stealthy Attack on Large Language Model based Recommendation](https://mlsanity.com/paper/2402.14836/) (2024)
- [Tapping the Potential of Large Language Models as Recommender Systems: A Comprehensive Framework and Empirical Analysis](https://mlsanity.com/paper/2401.04997/) (2024)
- [The Impact of Differential Privacy on Recommendation Accuracy and Popularity Bias](https://mlsanity.com/paper/2401.03883/) (2024)
- [Protecting User Privacy: An Approach for Untraceable Web Browsing History and Unambiguous User Profiles](https://mlsanity.com/paper/1811.09340/) (2018)
- [HARPO: Learning to Subvert Online Behavioral Advertising](https://mlsanity.com/paper/2111.05792/) (2021)
- [Echoes of Privacy: Uncovering the Profiling Practices of Voice Assistants](https://mlsanity.com/paper/2409.07444/) (2024)
- [A Utility-Preserving Obfuscation Approach for YouTube Recommendations](https://mlsanity.com/paper/2210.08136/) (2022)
- [Efficient Noise Mitigation for Enhancing Inference Accuracy in DNNs on Mixed-Signal Accelerators](https://mlsanity.com/paper/2409.18553/) (2024)

## Built on by (most cited first, 5 of 5)

- [VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis](https://mlsanity.com/paper/2505.18570/) (2025)
- [Position: Recommender Systems Should Move Beyond Platform-Centric Ranking toward Personal Agent-Mediated Recommendation](https://mlsanity.com/paper/2609.11942/) (2026)
- [Efficient Multi-Model Orchestration for Self-Hosted Large Language Models](https://mlsanity.com/paper/2512.22402/) (2025)
- [Multi-Level Modeling of Large Language Model Inference Latency and Energy via Hybrid Analytical--Machine-Learning Predictors](https://mlsanity.com/paper/2608.06723/) (2026)
- [AgentRecommender: LLM Agents Enable Customizable Recommender Systems on the User Side](https://mlsanity.com/paper/2609.31166/) (2026)

## Abstract (arXiv)

Large Language Model (LLM)-based recommendation systems leverage powerful language models to generate personalized suggestions by processing user interactions and preferences. Unlike traditional recommendation systems that rely on structured data and collaborative filtering, LLM-based models process textual and contextual information, often using cloud-based infrastructure. This raises privacy concerns, as user data is transmitted to remote servers, increasing the risk of exposure and reducing control over personal information. To address this, we propose a hybrid privacy-preserving recommendation framework which separates sensitive from nonsensitive data and only shares the latter with the cloud to harness LLM-powered recommendations. To restore lost recommendations related to obfuscated sensitive data, we design a de-obfuscation module that reconstructs sensitive recommendations locally. Experiments on real-world e-commerce datasets show that our framework achieves almost the same recommendation utility with a system which shares all data with an LLM, while preserving privacy to a large extend. Compared to obfuscation-only techniques, our approach improves HR@10 scores and category distribution alignment, offering a better balance between privacy and recommendation quality. Furthermore, our method runs efficiently on consumer-grade hardware, making privacy-aware LLM-based recommendation systems practical for real-world use.