# Confidential Deep Learning: Executing Proprietary Models on Untrusted Devices

arXiv: https://arxiv.org/abs/1908.10730 · HTML: https://mlsanity.com/paper/1908.10730/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Aug 2019.

## Built on by (most cited first, 3 of 3)

- [Machine Learning with Confidential Computing: A Systematization of Knowledge](https://mlsanity.com/paper/2208.10134/) (2022)
- [Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspective](https://mlsanity.com/paper/2111.03308/) (2021)
- [TBNet: A Neural Architectural Defense Framework Facilitating DNN Model Protection in Trusted Execution Environments](https://mlsanity.com/paper/2405.03974/) (2024)

## Abstract (arXiv)

Performing deep learning on end-user devices provides fast offline inference results and can help protect the user's privacy. However, running models on untrusted client devices reveals model information which may be proprietary, i.e., the operating system or other applications on end-user devices may be manipulated to copy and redistribute this information, infringing on the model provider's intellectual property. We propose the use of ARM TrustZone, a hardware-based security feature present in most phones, to confidentially run a proprietary model on an untrusted end-user device. We explore the limitations and design challenges of using TrustZone and examine potential approaches for confidential deep learning within this environment. Of particular interest is providing robust protection of proprietary model information while minimizing total performance overhead.