# Fairness and Robustness in Machine Unlearning

arXiv: https://arxiv.org/abs/2504.13610 · HTML: https://mlsanity.com/paper/2504.13610/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 12 of its 22 references that are in the map.
- First posted on arXiv 18 Apr 2025.

## Placed in

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

## Builds on (most cited first, 12 of 12)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [Single Image Unlearning: Efficient Machine Unlearning in Multimodal Large Language Models](https://mlsanity.com/paper/2405.12523/) (2024)
- [All but One: Surgical Concept Erasing with Model Preservation in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2312.12807/) (2023)
- [Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomy](https://mlsanity.com/paper/2312.10549/) (2023)
- [Selective Forgetting of Deep Networks at a Finer Level than Samples](https://mlsanity.com/paper/2012.11849/) (2020)

## Built on by (most cited first, 4 of 4)

- [Investigating Label Bias and Representational Sources of Age-Related Disparities in Medical Segmentation](https://mlsanity.com/paper/2511.00477/) (2025)
- [Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization](https://mlsanity.com/paper/2509.20230/) (2025)
- [Who Does Your Algorithm Fail? Investigating Age and Ethnic Bias in the MAMA-MIA Dataset](https://mlsanity.com/paper/2510.27421/) (2025)
- [Soft Weighted Machine Unlearning](https://mlsanity.com/paper/2505.18783/) (2025)

## Abstract (arXiv)

Machine unlearning poses the challenge of ``how to eliminate the influence of specific data from a pretrained model'' in regard to privacy concerns. While prior research on approximated unlearning has demonstrated accuracy and efficiency in time complexity, we claim that it falls short of achieving exact unlearning, and we are the first to focus on fairness and robustness in machine unlearning algorithms. Our study presents fairness Conjectures for a well-trained model, based on the variance-bias trade-off characteristic, and considers their relevance to robustness. Our Conjectures are supported by experiments conducted on the two most widely used model architectures, ResNet and ViT, demonstrating the correlation between fairness and robustness: textitthe higher fairness-gap is, the more the model is sensitive and vulnerable. In addition, our experiments demonstrate the vulnerability of current state-of-the-art approximated unlearning algorithms to adversarial attacks, where their unlearned models suffer a significant drop in accuracy compared to the exact-unlearned models. We claim that our fairness-gap measurement and robustness metric should be used to evaluate the unlearning algorithm. Furthermore, we demonstrate that unlearning in the intermediate and last layers is sufficient and cost-effective for time and memory complexity.