# To Be Forgotten or To Be Fair: Unveiling Fairness Implications of Machine Unlearning Methods

arXiv: https://arxiv.org/abs/2302.03350 · HTML: https://mlsanity.com/paper/2302.03350/

## Key facts

- Cited by 19 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 22 of its 58 references that are in the map.
- First posted on arXiv 7 Feb 2023.

## Placed in

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

## Builds on (most cited first, 22 of 22)

- [Equality of Opportunity in Supervised Learning](https://mlsanity.com/paper/1610.02413/) (2016)
- [A Survey on Bias and Fairness in Machine Learning](https://mlsanity.com/paper/1908.09635/) (2019)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Fair prediction with disparate impact: A study of bias in recidivism prediction instruments](https://mlsanity.com/paper/1610.07524/) (2016)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Certified Data Removal from Machine Learning Models](https://mlsanity.com/paper/1911.03030/) (2019)
- [Algorithmic decision making and the cost of fairness](https://mlsanity.com/paper/1701.08230/) (2017)
- [Preventing Fairness Gerrymandering: Auditing and Learning for Subgroup Fairness](https://mlsanity.com/paper/1711.05144/) (2017)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [The Computational Limits of Deep Learning](https://mlsanity.com/paper/2007.05558/) (2020)
- [Forgetting Outside the Box: Scrubbing Deep Networks of Information Accessible from Input-Output Observations](https://mlsanity.com/paper/2003.02960/) (2020)
- [Graph Unlearning](https://mlsanity.com/paper/2103.14991/) (2021)
- [Machine Unlearning: Linear Filtration for Logit-based Classifiers](https://mlsanity.com/paper/2002.02730/) (2020)
- [Recommendation Unlearning](https://mlsanity.com/paper/2201.06820/) (2022)
- [Automated Directed Fairness Testing](https://mlsanity.com/paper/1807.00468/) (2018)
- [Do the Machine Learning Models on a Crowd Sourced Platform Exhibit Bias? An Empirical Study on Model Fairness](https://mlsanity.com/paper/2005.12379/) (2020)
- [Automatic Testing and Improvement of Machine Translation](https://mlsanity.com/paper/1910.02688/) (2019)
- [Coded Machine Unlearning](https://mlsanity.com/paper/2012.15721/) (2020)
- [Enforcing Group Fairness in Algorithmic Decision Making: Utility Maximization Under Sufficiency](https://mlsanity.com/paper/2206.02237/) (2022)
- [Taming the Cross Entropy Loss](https://mlsanity.com/paper/1810.05075/) (2018)

## Built on by (most cited first, 19 of 19)

- [MUSE: Machine Unlearning Six-Way Evaluation for Language Models](https://mlsanity.com/paper/2407.06460/) (2024)
- [Right to be Forgotten in the Era of Large Language Models: Implications, Challenges, and Solutions](https://mlsanity.com/paper/2307.03941/) (2023)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [Fair Machine Unlearning: Data Removal while Mitigating Disparities](https://mlsanity.com/paper/2307.14754/) (2023)
- [Distillation Robustifies Unlearning](https://mlsanity.com/paper/2506.06278/) (2025)
- [FairSISA: Ensemble Post-Processing to Improve Fairness of Unlearning in LLMs](https://mlsanity.com/paper/2312.07420/) (2023)
- [Position: Bridge the Gaps between Machine Unlearning and AI Regulation](https://mlsanity.com/paper/2502.12430/) (2025)
- [Machine Unlearning: its nature, scope, and importance for a "delete culture"](https://mlsanity.com/paper/2305.15242/) (2023)
- [Reliable Unlearning Harmful Information in LLMs with Metamorphosis Representation Projection](https://mlsanity.com/paper/2508.15449/) (2025)
- [Debiasing Machine Unlearning with Counterfactual Examples](https://mlsanity.com/paper/2404.15760/) (2024)
- [Exploring Fairness in Educational Data Mining in the Context of the Right to be Forgotten](https://mlsanity.com/paper/2405.16798/) (2024)
- [Group-robust Machine Unlearning](https://mlsanity.com/paper/2503.09330/) (2025)
- [A Guide to Large Language Models in Modeling and Simulation: From Core Techniques to Critical Challenges](https://mlsanity.com/paper/2602.05883/) (2026)
- [Privacy-Aware Lifelong Learning](https://mlsanity.com/paper/2505.10941/) (2025)
- [Covert Attacks on Machine Learning Training in Passively Secure MPC](https://mlsanity.com/paper/2505.17092/) (2025)
- [Unlearning Algorithmic Biases over Graphs](https://mlsanity.com/paper/2505.14945/) (2025)
- [Controllable Machine Unlearning via Gradient Pivoting](https://mlsanity.com/paper/2510.19226/) (2025)
- [Interference-Aware Multi-Task Unlearning](https://mlsanity.com/paper/2605.19042/) (2026)
- [Modeling Deletion Requests in Machine Unlearning](https://mlsanity.com/paper/2610.04310/) (2026)

## Abstract (arXiv)

The right to be forgotten (RTBF) is motivated by the desire of people not to be perpetually disadvantaged by their past deeds. For this, data deletion needs to be deep and permanent, and should be removed from machine learning models. Researchers have proposed machine unlearning algorithms which aim to erase specific data from trained models more efficiently. However, these methods modify how data is fed into the model and how training is done, which may subsequently compromise AI ethics from the fairness perspective. To help software engineers make responsible decisions when adopting these unlearning methods, we present the first study on machine unlearning methods to reveal their fairness implications. We designed and conducted experiments on two typical machine unlearning methods (SISA and AmnesiacML) along with a retraining method (ORTR) as baseline using three fairness datasets under three different deletion strategies. Experimental results show that under non-uniform data deletion, SISA leads to better fairness compared with ORTR and AmnesiacML, while initial training and uniform data deletion do not necessarily affect the fairness of all three methods. These findings have exposed an important research problem in software engineering, and can help practitioners better understand the potential trade-offs on fairness when considering solutions for RTBF.