# Plinius: Secure and Persistent Machine Learning Model Training

arXiv: https://arxiv.org/abs/2104.02987 · HTML: https://mlsanity.com/paper/2104.02987/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 41 references that are in the map.
- First posted on arXiv 7 Apr 2021.

## Builds on (most cited first, 12 of 12)

- [Stealing Machine Learning Models via Prediction APIs](https://mlsanity.com/paper/1609.02943/) (2016)
- [Caffe: Convolutional Architecture for Fast Feature Embedding](https://mlsanity.com/paper/1408.5093/) (2014)
- [Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware](https://mlsanity.com/paper/1806.03287/) (2018)
- [Privacy Preserving Machine Learning: Threats and Solutions](https://mlsanity.com/paper/1804.11238/) (2018)
- [Chiron: Privacy-preserving Machine Learning as a Service](https://mlsanity.com/paper/1803.05961/) (2018)
- [MLCapsule: Guarded Offline Deployment of Machine Learning as a Service](https://mlsanity.com/paper/1808.00590/) (2018)
- [Efficient Deep Learning on Multi-Source Private Data](https://mlsanity.com/paper/1807.06689/) (2018)
- [secureTF: A Secure TensorFlow Framework](https://mlsanity.com/paper/2101.08204/) (2021)
- [Occlum: Secure and Efficient Multitasking Inside a Single Enclave of Intel SGX](https://mlsanity.com/paper/2001.07450/) (2020)
- [Basic Performance Measurements of the Intel Optane DC Persistent Memory Module](https://mlsanity.com/paper/1903.05714/) (2019)
- [Malware Guard Extension: Using SGX to Conceal Cache Attacks](https://mlsanity.com/paper/1702.08719/) (2017)
- [An Empirical Guide to the Behavior and Use of Scalable Persistent Memory](https://mlsanity.com/paper/1908.03583/) (2019)

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

- [Proof of Unlearning: Definitions and Instantiation](https://mlsanity.com/paper/2210.11334/) (2022)
- [A Survey of Secure Computation Using Trusted Execution Environments](https://mlsanity.com/paper/2302.12150/) (2023)
- [Memory-Efficient and Secure DNN Inference on TrustZone-enabled Consumer IoT Devices](https://mlsanity.com/paper/2403.12568/) (2024)

## Abstract (arXiv)

With the increasing popularity of cloud based machine learning (ML) techniques there comes a need for privacy and integrity guarantees for ML data. In addition, the significant scalability challenges faced by DRAM coupled with the high access-times of secondary storage represent a huge performance bottleneck for ML systems. While solutions exist to tackle the security aspect, performance remains an issue. Persistent memory (PM) is resilient to power loss (unlike DRAM), provides fast and fine-granular access to memory (unlike disk storage) and has latency and bandwidth close to DRAM (in the order of ns and GB/s, respectively). We present PLINIUS, a ML framework using Intel SGX enclaves for secure training of ML models and PM for fault tolerance guarantees. PLINIUS uses a novel mirroring mechanism to create and maintain (i) encrypted mirror copies of ML models on PM, and (ii) encrypted training data in byte-addressable PM, for near-instantaneous data recovery after a system failure. Compared to disk-based checkpointing systems, PLINIUS is 3.2x and 3.7x faster respectively for saving and restoring models on real PM hardware, achieving robust and secure ML model training in SGX enclaves.