# Machine Unlearning: A Comprehensive Survey

arXiv: https://arxiv.org/abs/2405.07406 · HTML: https://mlsanity.com/paper/2405.07406/

## Key facts

- Cited by 35 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 95 of its 172 references that are in the map.
- First posted on arXiv 13 May 2024.

## Placed in

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

## Builds on (most cited first, 30 of 95)

- [Communication-Efficient Learning of Deep Networks from Decentralized Data](https://mlsanity.com/paper/1602.05629/) (2016)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Fast Graph Representation Learning with PyTorch Geometric](https://mlsanity.com/paper/1903.02428/) (2019)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Open Graph Benchmark: Datasets for Machine Learning on Graphs](https://mlsanity.com/paper/2005.00687/) (2020)
- [Gradient Episodic Memory for Continual Learning](https://mlsanity.com/paper/1706.08840/) (2017)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Variational Inference: A Review for Statisticians](https://mlsanity.com/paper/1601.00670/) (2016)
- [Experience Replay for Continual Learning](https://mlsanity.com/paper/1811.11682/) (2018)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Pitfalls of Graph Neural Network Evaluation](https://mlsanity.com/paper/1811.05868/) (2018)
- [Revisiting Semi-Supervised Learning with Graph Embeddings](https://mlsanity.com/paper/1603.08861/) (2016)
- [Learning to Prompt for Continual Learning](https://mlsanity.com/paper/2112.08654/) (2021)
- [Image-based Recommendations on Styles and Substitutes](https://mlsanity.com/paper/1506.04757/) (2015)
- [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)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Efficient Processing of Deep Neural Networks: A Tutorial and Survey](https://mlsanity.com/paper/1703.09039/) (2017)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Recent Advances in Convolutional Neural Networks](https://mlsanity.com/paper/1512.07108/) (2015)
- [Adversarial Examples: Attacks and Defenses for Deep Learning](https://mlsanity.com/paper/1712.07107/) (2017)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Large Language Model Unlearning](https://mlsanity.com/paper/2310.10683/) (2023)
- [Unrolling SGD: Understanding Factors Influencing Machine Unlearning](https://mlsanity.com/paper/2109.13398/) (2021)
- [Rethinking Machine Unlearning for Large Language Models](https://mlsanity.com/paper/2402.08787/) (2024)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)

## Built on by (most cited first, 30 of 35)

- [A Comprehensive Survey in LLM(-Agent) Full Stack Safety: Data, Training and Deployment](https://mlsanity.com/paper/2504.15585/) (2025)
- [Learning to Unlearn while Retaining: Combating Gradient Conflicts in Machine Unlearning](https://mlsanity.com/paper/2503.06339/) (2025)
- [Erased or Dormant? Rethinking Concept Erasure Through Reversibility](https://mlsanity.com/paper/2505.16174/) (2025)
- [Forget Many, Forget Right: Scalable and Precise Concept Unlearning in Diffusion Models](https://mlsanity.com/paper/2601.06162/) (2026)
- [A Survey on Recommendation Unlearning: Fundamentals, Taxonomy, Evaluation, and Open Questions](https://mlsanity.com/paper/2412.12836/) (2024)
- [The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models](https://mlsanity.com/paper/2507.18725/) (2025)
- [Forget Vectors at Play: Universal Input Perturbations Driving Machine Unlearning in Image Classification](https://mlsanity.com/paper/2412.16780/) (2024)
- [Gaussian Certified Unlearning in High Dimensions: A Hypothesis Testing Approach](https://mlsanity.com/paper/2510.13094/) (2025)
- [A Survey on Unlearnable Data](https://mlsanity.com/paper/2503.23536/) (2025)
- [Deep Contrastive Unlearning for Language Models](https://mlsanity.com/paper/2503.14900/) (2025)
- [The Unseen Threat: Residual Knowledge in Machine Unlearning under Perturbed Samples](https://mlsanity.com/paper/2601.22359/) (2026)
- [Class Unlearning via Depth-Aware Removal of Forget-Specific Directions](https://mlsanity.com/paper/2604.15166/) (2026)
- [Learning to Forget using Hypernetworks](https://mlsanity.com/paper/2412.00761/) (2024)
- [Parameter-Efficient Token Embedding Editing for Clinical Class-Level Unlearning](https://mlsanity.com/paper/2603.19302/) (2026)
- [Visual-Noise Guided In-Context Distillation for Multimodal Large Language Model Unlearning](https://mlsanity.com/paper/2606.00105/) (2026)
- [Ready2Unlearn: A Learning-Time Approach for Preparing Models with Future Unlearning Readiness](https://mlsanity.com/paper/2505.10845/) (2025)
- [Efficient Machine Unlearning by Model Splitting and Core Sample Selection](https://mlsanity.com/paper/2505.07026/) (2025)
- [Losing is for Cherishing: Data Valuation Based on Machine Unlearning and Shapley Value](https://mlsanity.com/paper/2505.16147/) (2025)
- [Superior resilience to poisoning and amenability to unlearning in quantum machine learning](https://mlsanity.com/paper/2508.02422/) (2025)
- [CUFG: Curriculum Unlearning Guided by the Forgetting Gradient](https://mlsanity.com/paper/2509.14633/) (2025)
- [Beyond Sharp Minima: Robust LLM Unlearning via Feedback-Guided Multi-Point Optimization](https://mlsanity.com/paper/2509.20230/) (2025)
- [Improving Unlearning with Model Updates Probably Aligned with Gradients](https://mlsanity.com/paper/2511.02435/) (2025)
- [Statistical Roughness-Informed Machine Unlearning](https://mlsanity.com/paper/2602.09304/) (2026)
- [Designing to Forget: Deep Semi-parametric Models for Unlearning](https://mlsanity.com/paper/2603.22870/) (2026)
- [No Concept Escapes the Audit: Auditing-Aware Unlearning for Verifiable Concept Erasure in Diffusion Models](https://mlsanity.com/paper/2610.05401/) (2026)
- [Dark Miner: Defend against undesirable generation for text-to-image diffusion models](https://mlsanity.com/paper/2409.17682/) (2024)
- [Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical Images](https://mlsanity.com/paper/2505.21872/) (2025)
- [UNO: Unlearning via Orthogonalization in Generative models](https://mlsanity.com/paper/2506.04712/) (2025)
- [Unlearning of Knowledge Graph Embedding via Preference Optimization](https://mlsanity.com/paper/2507.20566/) (2025)
- [WIN-U: Woodbury-Informed Newton-Unlearning as a retain-free Machine Unlearning Framework](https://mlsanity.com/paper/2604.13438/) (2026)

## Abstract (arXiv)

As the right to be forgotten has been legislated worldwide, many studies attempt to design unlearning mechanisms to protect users' privacy when they want to leave machine learning service platforms. Specifically, machine unlearning is to make a trained model to remove the contribution of an erased subset of the training dataset. This survey aims to systematically classify a wide range of machine unlearning and discuss their differences, connections and open problems. We categorize current unlearning methods into four scenarios: centralized unlearning, distributed and irregular data unlearning, unlearning verification, and privacy and security issues in unlearning. Since centralized unlearning is the primary domain, we use two parts to introduce: firstly, we classify centralized unlearning into exact unlearning and approximate unlearning; secondly, we offer a detailed introduction to the techniques of these methods. Besides the centralized unlearning, we notice some studies about distributed and irregular data unlearning and introduce federated unlearning and graph unlearning as the two representative directions. After introducing unlearning methods, we review studies about unlearning verification. Moreover, we consider the privacy and security issues essential in machine unlearning and organize the latest related literature. Finally, we discuss the challenges of various unlearning scenarios and address the potential research directions.