# Privacy-preserving Machine Learning through Data Obfuscation

arXiv: https://arxiv.org/abs/1807.01860 · HTML: https://mlsanity.com/paper/1807.01860/

## Key facts

- Cited by 18 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 5 Jul 2018.

## Built on by (most cited first, 18 of 18)

- [Membership Inference Attacks on Machine Learning: A Survey](https://mlsanity.com/paper/2103.07853/) (2021)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [Privacy and Trust Redefined in Federated Machine Learning](https://mlsanity.com/paper/2103.15753/) (2021)
- [DeepBlur: A Simple and Effective Method for Natural Image Obfuscation](https://mlsanity.com/paper/2104.02655/) (2021)
- [All Rivers Run to the Sea: Private Learning with Asymmetric Flows](https://mlsanity.com/paper/2312.05264/) (2023)
- [Enterprise AI Must Enforce Participant-Aware Access Control](https://mlsanity.com/paper/2509.14608/) (2025)
- [Preserving Privacy in Personalized Models for Distributed Mobile Services](https://mlsanity.com/paper/2101.05855/) (2021)
- [On Responsible Machine Learning Datasets with Fairness, Privacy, and Regulatory Norms](https://mlsanity.com/paper/2310.15848/) (2023)
- [Proactive Schemes: A Survey of Adversarial Attacks for Social Good](https://mlsanity.com/paper/2409.16491/) (2024)
- [Game-Theoretic and Machine Learning-based Approaches for Defensive Deception: A Survey](https://mlsanity.com/paper/2101.10121/) (2021)
- [Synthetic Dataset Generation for Privacy-Preserving Machine Learning](https://mlsanity.com/paper/2210.03205/) (2022)
- [Memorization of Named Entities in Fine-tuned BERT Models](https://mlsanity.com/paper/2212.03749/) (2022)
- [Edge AI for Internet of Energy: Challenges and Perspectives](https://mlsanity.com/paper/2311.16851/) (2023)
- [Additive Logistic Mechanism for Privacy-Preserving Self-Supervised Learning](https://mlsanity.com/paper/2205.12430/) (2022)
- [Threats, Vulnerabilities, and Controls of Machine Learning Based Systems: A Survey and Taxonomy](https://mlsanity.com/paper/2301.07474/) (2023)
- [Data Privacy Preservation on the Internet of Things](https://mlsanity.com/paper/2304.00258/) (2023)
- [Privacy-Preserving Medical Image Classification through Deep Learning and Matrix Decomposition](https://mlsanity.com/paper/2308.16530/) (2023)
- [Inference Privacy: Properties and Mechanisms](https://mlsanity.com/paper/2411.18746/) (2024)

## Abstract (arXiv)

As machine learning becomes a practice and commodity, numerous cloud-based services and frameworks are provided to help customers develop and deploy machine learning applications. While it is prevalent to outsource model training and serving tasks in the cloud, it is important to protect the privacy of sensitive samples in the training dataset and prevent information leakage to untrusted third parties. Past work have shown that a malicious machine learning service provider or end user can easily extract critical information about the training samples, from the model parameters or even just model outputs. In this paper, we propose a novel and generic methodology to preserve the privacy of training data in machine learning applications. Specifically we introduce an obfuscate function and apply it to the training data before feeding them to the model training task. This function adds random noise to existing samples, or augments the dataset with new samples. By doing so sensitive information about the properties of individual samples, or statistical properties of a group of samples, is hidden. Meanwhile the model trained from the obfuscated dataset can still achieve high accuracy. With this approach, the customers can safely disclose the data or models to third-party providers or end users without the need to worry about data privacy. Our experiments show that this approach can effective defeat four existing types of machine learning privacy attacks at negligible accuracy cost.