PADER: Paillier-based Secure Decentralized Social Recommendation

2026-01-15

AI Summary

This work addresses the privacy risks inherent in centralized recommender systems by proposing a decentralized social recommendation framework that models users and merchants as nodes in a network. Leveraging the Paillier homomorphic encryption scheme, the framework enables secure training and inference of the SoReg model without exposing raw data. To the best of our knowledge, this is the first integration of the Paillier cryptosystem into decentralized social recommendation. The authors design efficient secure protocols for addition and multiplication, along with an optimized data packing strategy tailored for real-valued polynomial computations, significantly enhancing computational efficiency. Experimental results demonstrate practical feasibility: iterative processing of hundreds of ratings per user takes approximately one second, and a full epoch over 500,000 ratings completes in under three hours.

Technology Category

• Data Mining & Knowledge Management: Recommender Systems
• Machine Learning: Privacy
• Search and Optimization: Distributed Search

Application Category

• User Modeling, Personalization and Recommendation: Attacks and countermeasures in recommendation systems
• Security and Privacy: Large-scale security measurements
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

The prevalence of recommendation systems also brings privacy concerns to both the users and the sellers, as centralized platforms collect as much data as possible from them. To keep the data private, we propose PADER: a Paillier-based secure decentralized social recommendation system. In this system, the users and the sellers are nodes in a decentralized network. The training and inference of the recommendation model are carried out securely in a decentralized manner, without the involvement of a centralized platform. To this end, we apply the Paillier cryptosystem to the SoReg (Social Regularization) model, which exploits both user's ratings and social relations. We view the SoReg model as a two-party secure polynomial evaluation problem and observe that the simple bipartite computation may result in poor efficiency. To improve efficiency, we design secure addition and multiplication protocols to support secure computation on any arithmetic circuit, along with an optimal data packing scheme that is suitable for the polynomial computations of real values. Experiment results show that our method only takes about one second to iterate through one user with hundreds of ratings, and training with ~500K ratings for one epoch only takes<3 hours, which shows that the method is practical in real applications. The code is available at https://github.com/GarminQ/PADER.

Problem

• privacy
• decentralized recommendation
• social recommendation
• secure computation
• data protection

Innovation

• Paillier cryptosystem
• decentralized recommendation
• secure multi-party computation
• social regularization
• data packing