Graviton: Trusted Execution Environments on GPUs

By Stavros Volos, Kapil Vaswani, R. Bruno. 2018

266 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

1. Yoshua Bengio
2. Peter Henderson
3. Sara Hooker
4. Bo Li
5. Sergey Levine
6. David Krueger
7. Pang Wei Koh
8. Shagun Sodhani

Citations in the corpus

• Toward Trustworthy AI Development: Mechanisms for Supporting Verifiable Claims (2020, background): “67 Demonstrations to date have been carried out on commodity hardware (CPUs [113] [114] and GPUs [115]) or have secure and verifiable outsourcing of parts of the computation to less secure hardware [116] [117], rather than on hardware directly optimized for machine learning (such as TPUs).”
• DeepAttest: An End-to-End Attestation Framework for Deep Neural Networks (2019, methodology): “More specifically, the weight data stored in the untrusted DRAM is first encrypted by our GPU simulator using authenticated encryption (AES in GCM mode) and copied to the secure memory [49].”
• Occlumency: Privacy-preserving Remote Deep-learning Inference Using SGX (2019, methodology): “Building a trusted execution environment for GPU and enabling DL inference in the environment remains as an important future research direction [72].”