# Proteus: Preserving Model Confidentiality during Graph Optimizations

arXiv: https://arxiv.org/abs/2404.12512 · HTML: https://mlsanity.com/paper/2404.12512/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 45 references that are in the map.
- First posted on arXiv 18 Apr 2024.

## Builds on (most cited first, 17 of 17)

- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [High-Resolution Image Synthesis with Latent Diffusion Models](https://mlsanity.com/paper/2112.10752/) (2021)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Inductive Representation Learning on Large Graphs](https://mlsanity.com/paper/1706.02216/) (2017)
- [Squeeze-and-Excitation Networks](https://mlsanity.com/paper/1709.01507/) (2017)
- [Learning Transferable Architectures for Scalable Image Recognition](https://mlsanity.com/paper/1707.07012/) (2017)
- [Practical Black-Box Attacks against Machine Learning](https://mlsanity.com/paper/1602.02697/) (2016)
- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [GraphRNN: Generating Realistic Graphs with Deep Auto-regressive Models](https://mlsanity.com/paper/1802.08773/) (2018)
- [Ansor: Generating High-Performance Tensor Programs for Deep Learning](https://mlsanity.com/paper/2006.06762/) (2020)
- [Stealing Hyperparameters in Machine Learning](https://mlsanity.com/paper/1802.05351/) (2018)
- [NATS-Bench: Benchmarking NAS Algorithms for Architecture Topology and Size](https://mlsanity.com/paper/2009.00437/) (2020)
- [Glow: Graph Lowering Compiler Techniques for Neural Networks](https://mlsanity.com/paper/1805.00907/) (2018)
- [CryptoDL: Deep Neural Networks over Encrypted Data](https://mlsanity.com/paper/1711.05189/) (2017)
- [SparseTIR: Composable Abstractions for Sparse Compilation in Deep Learning](https://mlsanity.com/paper/2207.04606/) (2022)
- [Hidet: Task-Mapping Programming Paradigm for Deep Learning Tensor Programs](https://mlsanity.com/paper/2210.09603/) (2022)
- [Intel nGraph: An Intermediate Representation, Compiler, and Executor for Deep Learning](https://mlsanity.com/paper/1801.08058/) (2018)

## Built on by (most cited first, 1 of 1)

- [LayerDAG: A Layerwise Autoregressive Diffusion Model for Directed Acyclic Graph Generation](https://mlsanity.com/paper/2411.02322/) (2024)

## Abstract (arXiv)

Deep learning (DL) models have revolutionized numerous domains, yet optimizing them for computational efficiency remains a challenging endeavor. Development of new DL models typically involves two parties: the model developers and performance optimizers. The collaboration between the parties often necessitates the model developers exposing the model architecture and computational graph to the optimizers. However, this exposure is undesirable since the model architecture is an important intellectual property, and its innovations require significant investments and expertise. During the exchange, the model is also vulnerable to adversarial attacks via model stealing. This paper presents Proteus, a novel mechanism that enables model optimization by an independent party while preserving the confidentiality of the model architecture. Proteus obfuscates the protected model by partitioning its computational graph into subgraphs and concealing each subgraph within a large pool of generated realistic subgraphs that cannot be easily distinguished from the original. We evaluate Proteus on a range of DNNs, demonstrating its efficacy in preserving confidentiality without compromising performance optimization opportunities. Proteus effectively hides the model as one alternative among up to 1032 possible model architectures, and is resilient against attacks with a learning-based adversary. We also demonstrate that heuristic based and manual approaches are ineffective in identifying the protected model. To our knowledge, Proteus is the first work that tackles the challenge of model confidentiality during performance optimization. Proteus will be open-sourced for direct use and experimentation, with easy integration with compilers such as ONNXRuntime.