Privacy and Integrity Preserving Training Using Trusted Hardware
arXiv:2105.00334
Abstract
Privacy and security-related concerns are growing as machine learning reaches diverse application domains. The data holders want to train with private data while exploiting accelerators, such as GPUs, that are hosted in the cloud. However, Cloud systems are vulnerable to attackers that compromise the privacy of data and integrity of computations. This work presents DarKnight, a framework for large DNN training while protecting input privacy and computation integrity. DarKnight relies on cooperative execution between trusted execution environments (TEE) and accelerators, where the TEE provides privacy and integrity verification, while accelerators perform the computation heavy linear algebraic operations.
References in corpus (11)
- Very Deep Convolutional Networks for Large-Scale Image Recognition
- Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware
- DarkneTZ: Towards Model Privacy at the Edge using Trusted Execution Environments
- Chiron: Privacy-preserving Machine Learning as a Service
- Privacy in Deep Learning: A Survey
- Efficient Deep Learning on Multi-Source Private Data
- CodedPrivateML: A Fast and Privacy-Preserving Framework for Distributed Machine Learning
- Privacy-Preserving Inference in Machine Learning Services Using Trusted Execution Environments
- Is Private Learning Possible with Instance Encoding?
- Secure multiparty computations in floating-point arithmetic
- GOAT: GPU Outsourcing of Deep Learning Training With Asynchronous Probabilistic Integrity Verification Inside Trusted Execution Environment