TEE-based decentralized recommender systems: The raw data sharing redemption
arXiv:2202.11655 · doi:10.1109/IPDPS53621.2022.00050
Abstract
Recommenders are central in many applications today. The most effective recommendation schemes, such as those based on collaborative filtering (CF), exploit similarities between user profiles to make recommendations, but potentially expose private data. Federated learning and decentralized learning systems address this by letting the data stay on user's machines to preserve privacy: each user performs the training on local data and only the model parameters are shared. However, sharing the model parameters across the network may still yield privacy breaches. In this paper, we present REX, the first enclave-based decentralized CF recommender. REX exploits Trusted execution environments (TEE), such as Intel software guard extensions (SGX), that provide shielded environments within the processor to improve convergence while preserving privacy. Firstly, REX enables raw data sharing, which ultimately speeds up convergence and reduces the network load. Secondly, REX fully preserves privacy. We analyze the impact of raw data sharing in both deep neural network (DNN) and matrix factorization (MF) recommenders and showcase the benefits of trusted environments in a full-fledged implementation of REX. Our experimental results demonstrate that through raw data sharing, REX significantly decreases the training time by 18.3x and the network load by 2 orders of magnitude over standard decentralized approaches that share only parameters, while fully protecting privacy by leveraging trustworthy hardware enclaves with very little overhead.
References in corpus (14)
- Adam: A Method for Stochastic Optimization
- Deep Gradient Compression: Reducing the Communication Bandwidth for Distributed Training
- Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
- Communication Compression for Decentralized Training
- A Unified Theory of Decentralized SGD with Changing Topology and Local Updates
- Gossip Learning with Linear Models on Fully Distributed Data
- White-box vs Black-box: Bayes Optimal Strategies for Membership Inference
- Decentralized Collaborative Learning of Personalized Models over Networks
- SGX-Aware Container Orchestration for Heterogeneous Clusters
- Personalized and Private Peer-to-Peer Machine Learning
- CYCLOSA: Decentralizing Private Web Search Through SGX-Based Browser Extensions
- Asynchronous Decentralized SGD with Quantized and Local Updates
- MAGE: Mutual Attestation for a Group of Enclaves without Trusted Third Parties
- Malware in the SGX supply chain: Be careful when signing enclaves!