# Privacy Preservation through Practical Machine Unlearning

arXiv: https://arxiv.org/abs/2502.10635 · HTML: https://mlsanity.com/paper/2502.10635/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 5 of its 20 references that are in the map.
- First posted on arXiv 15 Feb 2025.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 5 of 5)

- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Machine Unlearning for Random Forests](https://mlsanity.com/paper/2009.05567/) (2020)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [Learn What You Want to Unlearn: Unlearning Inversion Attacks against Machine Unlearning](https://mlsanity.com/paper/2404.03233/) (2024)
- [Task-Aware Machine Unlearning and Its Application in Load Forecasting](https://mlsanity.com/paper/2308.14412/) (2023)

## Abstract (arXiv)

Machine Learning models thrive on vast datasets, continuously adapting to provide accurate predictions and recommendations. However, in an era dominated by privacy concerns, Machine Unlearning emerges as a transformative approach, enabling the selective removal of data from trained models. This paper examines methods such as Naive Retraining and Exact Unlearning via the SISA framework, evaluating their Computational Costs, Consistency, and feasibility using the textttHSpam14 dataset. We explore the potential of integrating unlearning principles into Positive Unlabeled (PU) Learning to address challenges posed by partially labeled datasets. Our findings highlight the promise of unlearning frameworks like textitDaRE for ensuring privacy compliance while maintaining model performance, albeit with significant computational trade-offs. This study underscores the importance of Machine Unlearning in achieving ethical AI and fostering trust in data-driven systems.