# Chiron: Privacy-preserving Machine Learning as a Service

arXiv: https://arxiv.org/abs/1803.05961 · HTML: https://mlsanity.com/paper/1803.05961/

## Key facts

- Cited by 40 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Mar 2018.

## Built on by (most cited first, 30 of 40)

- [PPFL: Privacy-preserving Federated Learning with Trusted Execution Environments](https://mlsanity.com/paper/2104.14380/) (2021)
- [Robust Machine Learning Systems: Challenges, Current Trends, Perspectives, and the Road Ahead](https://mlsanity.com/paper/2101.02559/) (2021)
- [Foundation Models for the Electric Power Grid](https://mlsanity.com/paper/2407.09434/) (2024)
- [A Survey on Model Extraction Attacks and Defenses for Large Language Models](https://mlsanity.com/paper/2506.22521/) (2025)
- [Towards Energy-Efficient and Secure Edge AI: A Cross-Layer Framework](https://mlsanity.com/paper/2109.09829/) (2021)
- [Machine Learning with Confidential Computing: A Systematization of Knowledge](https://mlsanity.com/paper/2208.10134/) (2022)
- [Proof of Unlearning: Definitions and Instantiation](https://mlsanity.com/paper/2210.11334/) (2022)
- [Citadel: Protecting Data Privacy and Model Confidentiality for Collaborative Learning with SGX](https://mlsanity.com/paper/2105.01281/) (2021)
- [Sisyphus: A Cautionary Tale of Using Low-Degree Polynomial Activations in Privacy-Preserving Deep Learning](https://mlsanity.com/paper/2107.12342/) (2021)
- [DarKnight: An Accelerated Framework for Privacy and Integrity Preserving Deep Learning Using Trusted Hardware](https://mlsanity.com/paper/2207.00083/) (2022)
- [secureTF: A Secure TensorFlow Framework](https://mlsanity.com/paper/2101.08204/) (2021)
- [Blockchain-based Federated Learning with Secure Aggregation in Trusted Execution Environment for Internet-of-Things](https://mlsanity.com/paper/2304.12889/) (2023)
- [Separation of Powers in Federated Learning](https://mlsanity.com/paper/2105.09400/) (2021)
- [A Survey of Secure Computation Using Trusted Execution Environments](https://mlsanity.com/paper/2302.12150/) (2023)
- [Blind quantum machine learning with quantum bipartite correlator](https://mlsanity.com/paper/2310.12893/) (2023)
- [State-of-the-Art Approaches to Enhancing Privacy Preservation of Machine Learning Datasets: A Survey](https://mlsanity.com/paper/2404.16847/) (2024)
- [Confidential Machine Learning Computation in Untrusted Environments: A Systems Security Perspective](https://mlsanity.com/paper/2111.03308/) (2021)
- [OLIVE: Oblivious Federated Learning on Trusted Execution Environment against the risk of sparsification](https://mlsanity.com/paper/2202.07165/) (2022)
- [SMLT: A Serverless Framework for Scalable and Adaptive Machine Learning Design and Training](https://mlsanity.com/paper/2205.01853/) (2022)
- [Plinius: Secure and Persistent Machine Learning Model Training](https://mlsanity.com/paper/2104.02987/) (2021)
- [Memory-Efficient Deep Learning Inference in Trusted Execution Environments](https://mlsanity.com/paper/2104.15109/) (2021)
- [Intellectual Property in Graph-Based Machine Learning as a Service: Attacks and Defenses](https://mlsanity.com/paper/2508.19641/) (2025)
- [Preserving Privacy in Personalized Models for Distributed Mobile Services](https://mlsanity.com/paper/2101.05855/) (2021)
- [Perun: Secure Multi-Stakeholder Machine Learning Framework with GPU Support](https://mlsanity.com/paper/2103.16898/) (2021)
- [Confidential Machine Learning within Graphcore IPUs](https://mlsanity.com/paper/2205.09005/) (2022)
- [Dash: Accelerating Distributed Private Convolutional Neural Network Inference with Arithmetic Garbled Circuits](https://mlsanity.com/paper/2302.06361/) (2023)
- [Inference Attacks: A Taxonomy, Survey, and Promising Directions](https://mlsanity.com/paper/2406.02027/) (2024)
- [Dstack: A Zero Trust Framework for Confidential Containers](https://mlsanity.com/paper/2509.11555/) (2025)
- [S++: A Fast and Deployable Secure-Computation Framework for Privacy-Preserving Neural Network Training](https://mlsanity.com/paper/2101.12078/) (2021)
- [Machine Learning Models Disclosure from Trusted Research Environments (TRE), Challenges and Opportunities](https://mlsanity.com/paper/2111.05628/) (2021)

## Abstract (arXiv)

Major cloud operators offer machine learning (ML) as a service, enabling customers who have the data but not ML expertise or infrastructure to train predictive models on this data. Existing ML-as-a-service platforms require users to reveal all training data to the service operator. We design, implement, and evaluate Chiron, a system for privacy-preserving machine learning as a service. First, Chiron conceals the training data from the service operator. Second, in keeping with how many existing ML-as-a-service platforms work, Chiron reveals neither the training algorithm nor the model structure to the user, providing only black-box access to the trained model. Chiron is implemented using SGX enclaves, but SGX alone does not achieve the dual goals of data privacy and model confidentiality. Chiron runs the standard ML training toolchain (including the popular Theano framework and C compiler) in an enclave, but the untrusted model-creation code from the service operator is further confined in a Ryoan sandbox to prevent it from leaking the training data outside the enclave. To support distributed training, Chiron executes multiple concurrent enclaves that exchange model parameters via a parameter server. We evaluate Chiron on popular deep learning models, focusing on benchmark image classification tasks such as CIFAR and ImageNet, and show that its training performance and accuracy of the resulting models are practical for common uses of ML-as-a-service.