# Evaluating Privacy-Preserving Machine Learning in Critical Infrastructures: A Case Study on Time-Series Classification

arXiv: https://arxiv.org/abs/2111.14838 · HTML: https://mlsanity.com/paper/2111.14838/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 15 of its 33 references that are in the map.
- First posted on arXiv 29 Nov 2021.

## Builds on (most cited first, 15 of 15)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [R'enyi Differential Privacy of the Sampled Gaussian Mechanism](https://mlsanity.com/paper/1908.10530/) (2019)
- [CrypTen: Secure Multi-Party Computation Meets Machine Learning](https://mlsanity.com/paper/2109.00984/) (2021)
- [Model Reconstruction from Model Explanations](https://mlsanity.com/paper/1807.05185/) (2018)
- [Privacy Preserving Machine Learning: Threats and Solutions](https://mlsanity.com/paper/1804.11238/) (2018)
- [Differential Privacy and Machine Learning: a Survey and Review](https://mlsanity.com/paper/1412.7584/) (2014)
- [Privacy-preserving Neural Representations of Text](https://mlsanity.com/paper/1808.09408/) (2018)
- [Differentially Private Empirical Risk Minimization with Input Perturbation](https://mlsanity.com/paper/1710.07425/) (2017)
- [Private Machine Learning in TensorFlow using Secure Computation](https://mlsanity.com/paper/1810.08130/) (2018)
- [Privacy-Aware Time-Series Data Sharing with Deep Reinforcement Learning](https://mlsanity.com/paper/2003.02685/) (2020)
- [Challenges of Privacy-Preserving Machine Learning in IoT](https://mlsanity.com/paper/1909.09804/) (2019)

## Built on by (most cited first, 6 of 6)

- [Lightweight Online Adaption for Time Series Foundation Model Forecasts](https://mlsanity.com/paper/2502.12920/) (2025)
- [Privacy Meets Explainability: A Comprehensive Impact Benchmark](https://mlsanity.com/paper/2211.04110/) (2022)
- [PrIeD-KIE: Towards Privacy Preserved Document Key Information Extraction](https://mlsanity.com/paper/2310.03777/) (2023)
- [Adapting Time Series Foundation Models through Data Mixtures](https://mlsanity.com/paper/2603.02840/) (2026)
- [DP-DocLDM: Differentially Private Document Image Generation using Latent Diffusion Models](https://mlsanity.com/paper/2508.04208/) (2025)
- [SoK: Assessing the State of Applied Federated Machine Learning](https://mlsanity.com/paper/2308.02454/) (2023)

## Abstract (arXiv)

With the advent of machine learning in applications of critical infrastructure such as healthcare and energy, privacy is a growing concern in the minds of stakeholders. It is pivotal to ensure that neither the model nor the data can be used to extract sensitive information used by attackers against individuals or to harm whole societies through the exploitation of critical infrastructure. The applicability of machine learning in these domains is mostly limited due to a lack of trust regarding the transparency and the privacy constraints. Various safety-critical use cases (mostly relying on time-series data) are currently underrepresented in privacy-related considerations. By evaluating several privacy-preserving methods regarding their applicability on time-series data, we validated the inefficacy of encryption for deep learning, the strong dataset dependence of differential privacy, and the broad applicability of federated methods.