# k-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers

arXiv: https://arxiv.org/abs/2102.04763 · HTML: https://mlsanity.com/paper/2102.04763/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 2 of its 46 references that are in the map.
- First posted on arXiv 9 Feb 2021.

## Builds on (most cited first, 2 of 2)

- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- [The Limits of Differential Privacy (and its Misuse in Data Release and Machine Learning)](https://mlsanity.com/paper/2011.02352/) (2020)

## Built on by (most cited first, 12 of 12)

- [The privacy issue of counterfactual explanations: explanation linkage attacks](https://mlsanity.com/paper/2210.12051/) (2022)
- [Synthetic Data: Revisiting the Privacy-Utility Trade-off](https://mlsanity.com/paper/2407.07926/) (2024)
- [Energy cost and machine learning accuracy impact of k-anonymisation and synthetic data techniques](https://mlsanity.com/paper/2305.07116/) (2023)
- [Privacy-Preserving Taxi-Demand Prediction Using Federated Learning](https://mlsanity.com/paper/2305.08107/) (2023)
- [Anonymous Bandits for Multi-User Systems](https://mlsanity.com/paper/2210.12198/) (2022)
- [Comparison of machine learning models applied on anonymized data with different techniques](https://mlsanity.com/paper/2305.07415/) (2023)
- [Intermediate Outputs Are More Sensitive Than You Think](https://mlsanity.com/paper/2412.00696/) (2024)
- [Multi-Objective Optimization-Based Anonymization of Structured Data for Machine Learning Application](https://mlsanity.com/paper/2501.01002/) (2025)
- [HyObscure: Hybrid Obscuring for Privacy-Preserving Data Publishing](https://mlsanity.com/paper/2112.07850/) (2021)
- [Delete My Account: Impact of Data Deletion on Machine Learning Classifiers](https://mlsanity.com/paper/2311.10385/) (2023)
- [AI Security Map: Holistic Organization of AI Security Technologies and Impacts on Stakeholders](https://mlsanity.com/paper/2508.08583/) (2025)
- [AnonShield: Scalable On-Premise Pseudonymization for CSIRT Vulnerability Data](https://mlsanity.com/paper/2606.15650/) (2026)

## Abstract (arXiv)

The protection of private information is a crucial issue in data-driven research and business contexts. Typically, techniques like anonymisation or (selective) deletion are introduced in order to allow data sharing, e. g. in the case of collaborative research endeavours. For use with anonymisation techniques, the k-anonymity criterion is one of the most popular, with numerous scientific publications on different algorithms and metrics. Anonymisation techniques often require changing the data and thus necessarily affect the results of machine learning models trained on the underlying data. In this work, we conduct a systematic comparison and detailed investigation into the effects of different k-anonymisation algorithms on the results of machine learning models. We investigate a set of popular k-anonymisation algorithms with different classifiers and evaluate them on different real-world datasets. Our systematic evaluation shows that with an increasingly strong k-anonymity constraint, the classification performance generally degrades, but to varying degrees and strongly depending on the dataset and anonymisation method. Furthermore, Mondrian can be considered as the method with the most appealing properties for subsequent classification.