# Comparison of machine learning models applied on anonymized data with different techniques

arXiv: https://arxiv.org/abs/2305.07415 · HTML: https://mlsanity.com/paper/2305.07415/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 24 references that are in the map.
- First posted on arXiv 12 May 2023.

## Builds on (most cited first, 4 of 4)

- [k-Anonymity in Practice: How Generalisation and Suppression Affect Machine Learning Classifiers](https://mlsanity.com/paper/2102.04763/) (2021)
- [Study of the performance and scalability of federated learning for medical imaging with intermittent clients](https://mlsanity.com/paper/2207.08581/) (2022)
- [Anonymizing Machine Learning Models](https://mlsanity.com/paper/2007.13086/) (2020)
- [pyCANON: A Python library to check the level of anonymity of a dataset](https://mlsanity.com/paper/2208.07556/) (2022)

## Built on by (most cited first, 1 of 1)

- [ClustEm4Ano: Clustering Text Embeddings of Nominal Textual Attributes for Microdata Anonymization](https://mlsanity.com/paper/2412.12649/) (2024)

## Abstract (arXiv)

Anonymization techniques based on obfuscating the quasi-identifiers by means of value generalization hierarchies are widely used to achieve preset levels of privacy. To prevent different types of attacks against database privacy it is necessary to apply several anonymization techniques beyond the classical k-anonymity or ℓ-diversity. However, the application of these methods is directly connected to a reduction of their utility in prediction and decision making tasks. In this work we study four classical machine learning methods currently used for classification purposes in order to analyze the results as a function of the anonymization techniques applied and the parameters selected for each of them. The performance of these models is studied when varying the value of k for k-anonymity and additional tools such as ℓ-diversity, t-closeness and δ-disclosure privacy are also deployed on the well-known adult dataset.