# Adversarial Mixup Unlearning

arXiv: https://arxiv.org/abs/2502.10288 · HTML: https://mlsanity.com/paper/2502.10288/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- First posted on arXiv 14 Feb 2025.

## Placed in

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

## Built on by (most cited first, 7 of 7)

- [Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness](https://mlsanity.com/paper/2505.10845/) (2025)
- [Reveal and Release: Iterative LLM Unlearning with Self-generated Data](https://mlsanity.com/paper/2509.14624/) (2025)
- [AUVIC: Adversarial Unlearning of Visual Concepts for Multi-modal Large Language Models](https://mlsanity.com/paper/2511.11299/) (2025)
- [Task-Agnostic Federation over Decentralized Data: Research Landscape and Visions](https://mlsanity.com/paper/2503.03140/) (2025)
- [Conformal Unlearning: A New Paradigm for Unlearning in Conformal Predictors](https://mlsanity.com/paper/2508.03245/) (2025)
- [Image Feature Fusion-based Federated Client Unlearning (FCU)](https://mlsanity.com/paper/2605.26715/) (2026)
- [On-the-go Forgetting without Explicit Unlearning via ERASE](https://mlsanity.com/paper/2609.05966/) (2026)

## Abstract (arXiv)

Machine unlearning is a critical area of research aimed at safeguarding data privacy by enabling the removal of sensitive information from machine learning models. One unique challenge in this field is catastrophic unlearning, where erasing specific data from a well-trained model unintentionally removes essential knowledge, causing the model to deviate significantly from a retrained one. To address this, we introduce a novel approach that regularizes the unlearning process by utilizing synthesized mixup samples, which simulate the data susceptible to catastrophic effects. At the core of our approach is a generator-unlearner framework, MixUnlearn, where a generator adversarially produces challenging mixup examples, and the unlearner effectively forgets target information based on these synthesized data. Specifically, we first introduce a novel contrastive objective to train the generator in an adversarial direction: generating examples that prompt the unlearner to reveal information that should be forgotten, while losing essential knowledge. Then the unlearner, guided by two other contrastive loss terms, processes the synthesized and real data jointly to ensure accurate unlearning without losing critical knowledge, overcoming catastrophic effects. Extensive evaluations across benchmark datasets demonstrate that our method significantly outperforms state-of-the-art approaches, offering a robust solution to machine unlearning. This work not only deepens understanding of unlearning mechanisms but also lays the foundation for effective machine unlearning with mixup augmentation.