Efficient Deep Learning on Multi-Source Private Data
By Nicholas Hynes, Raymond Cheng, Dawn Song. 2018
106 citations recorded by the source corpus.
Machine learning models benefit from large and diverse datasets. Using such datasets, however, often requires trusting a centralized data aggregator. For sensitive applications like healthcare and finance this is undesirable as it could compromise patient privacy or divulge trade secrets. Recent advances in secure and privacy-preserving computation, including trusted hardware enclaves and differential privacy, offer a way for mutually distrusting parties to efficiently train a machine learning model without revealing the training data. In this work, we introduce Myelin, a deep learning framework which combines these privacy-preservation primitives, and use it to establish a baseline level of performance for fully private machine learning.
Subfields: Artificial Intelligence
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Percy Liang
- Mohit Bansal
- Yoshua Bengio
- Jianfeng Gao
- Luke S. Zettlemoyer
- Yejin Choi
- Noah A. Smith
- Sergey Levine
Citations in the corpus
- Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020, background): “4% [112].”
- YerbaBuena: Securing Deep Learning Inference Data via Enclave-based Ternary Model Partitioning (2018, methodology): “We have discussed and compared with recent research efforts[22, 23, 38] of employing SGX for privacy-preserving machine learning tasks.”
- DarkneTZ: towards model privacy at the edge using trusted execution environments (2020, unknown): “Several other studies improved the efficiency of TEE-resident models using Graphics Processing Units (GPU) [51], multiple memory blocks [24], and high-performance ML frameworks [25].”
- DarKnight: A Data Privacy Scheme for Training and Inference of Deep Neural Networks (2020, methodology): “Our idea relies on TEEs to perform private inference or training in a secure hardware [5, 6, 7, 8, 9, 10].”
- Opacus: User-Friendly Differential Privacy Library in PyTorch (2021, unknown): “Last, we point to some efforts to perform ML training under different notions of privacy and security: the Myelin system makes use of secure hardware to add noise centrally [6], while Crypten [7] does training in a secure multi-party setting, without explicit noise addition.”