# Privacy Preserving Machine Learning Workflow: from Anonymization to Personalized Differential Privacy Budgets in Federated Learning

arXiv: https://arxiv.org/abs/2605.02372 · HTML: https://mlsanity.com/paper/2605.02372/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 25 references that are in the map.
- First posted on arXiv 4 May 2026.

## Builds on (most cited first, 8 of 8)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Privacy and Robustness in Federated Learning: Attacks and Defenses](https://mlsanity.com/paper/2012.06337/) (2020)
- [Deep Learning for Medical Image Processing: Overview, Challenges and Future](https://mlsanity.com/paper/1704.06825/) (2017)
- [Survey on Federated Learning Threats: concepts, taxonomy on attacks and defences, experimental study and challenges](https://mlsanity.com/paper/2201.08135/) (2022)
- [Federated Learning for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2306.05980/) (2023)
- [Personalized Federated Learning for improving radar based precipitation nowcasting on heterogeneous areas](https://mlsanity.com/paper/2408.05761/) (2024)
- [An Open Source Python Library for Anonymizing Sensitive Data](https://mlsanity.com/paper/2408.10766/) (2024)
- [pyCANON: A Python library to check the level of anonymity of a dataset](https://mlsanity.com/paper/2208.07556/) (2022)

## Abstract (arXiv)

The growing development of artificial intelligence based solutions, together with privacy legislation, has driven the rise of the so-called privacy preserving machine learning architectures, such as federated learning. While federated learning enables model training on decentralized data preventing their sharing and centralization, it still faces several challenges related to data integrity and privacy. This paper presents a comprehensive privacy preserving federated learning workflow for sensitive tabular data, including anonymization and differential privacy techniques. We also introduce a formal definition for the concept of client drift, together with ways of detecting it to mitigate poisoning attacks. Then, we detail a complete methodology for assigning personalized privacy budgets for global differential privacy to the different clients participating in the network, based on a re-identification risk metric. The proposed methodology is presented and tested on an openly available dataset of medical records. Within the experimental setup we show that the approach based on personalized budgets, compared to the architecture including global differential privacy with fixed privacy budget, achieves a better model performance in terms of two error metrics.