# Machine Unlearning via Null Space Calibration

arXiv: https://arxiv.org/abs/2404.13588 · HTML: https://mlsanity.com/paper/2404.13588/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 23 of its 32 references that are in the map.
- First posted on arXiv 21 Apr 2024.

## Placed in

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

## Builds on (most cited first, 23 of 23)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [A Convergence Theory for Deep Learning via Over-Parameterization](https://mlsanity.com/paper/1811.03962/) (2018)
- [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)
- [SalUn: Empowering Machine Unlearning via Gradient-based Weight Saliency in Both Image Classification and Generation](https://mlsanity.com/paper/2310.12508/) (2023)
- [Measuring the Intrinsic Dimension of Objective Landscapes](https://mlsanity.com/paper/1804.08838/) (2018)
- [Orthogonal Gradient Descent for Continual Learning](https://mlsanity.com/paper/1910.07104/) (2019)
- [Gradient Projection Memory for Continual Learning](https://mlsanity.com/paper/2103.09762/) (2021)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [Gradient Descent Happens in a Tiny Subspace](https://mlsanity.com/paper/1812.04754/) (2018)
- [Training Networks in Null Space of Feature Covariance for Continual Learning](https://mlsanity.com/paper/2103.07113/) (2021)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [Certified Robustness to Label-Flipping Attacks via Randomized Smoothing](https://mlsanity.com/paper/2002.03018/) (2020)
- [A Duty to Forget, a Right to be Assured? Exposing Vulnerabilities in Machine Unlearning Services](https://mlsanity.com/paper/2309.08230/) (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, 21 of 21)

- [Machine Unlearning Fails to Remove Data Poisoning Attacks](https://mlsanity.com/paper/2406.17216/) (2024)
- [SPEED: Scalable, Precise, and Efficient Concept Erasure for Diffusion Models](https://mlsanity.com/paper/2503.07392/) (2025)
- [Are We Truly Forgetting? A Critical Re-examination of Machine Unlearning Evaluation Protocols](https://mlsanity.com/paper/2503.06991/) (2025)
- [Class Machine Unlearning for Complex Data via Concepts Inference and Data Poisoning](https://mlsanity.com/paper/2405.15662/) (2024)
- [Erase at the Core: Representation Unlearning for Machine Unlearning](https://mlsanity.com/paper/2602.05375/) (2026)
- [Toward Efficient Data-Free Unlearning](https://mlsanity.com/paper/2412.13790/) (2024)
- [Machine Unlearning under Overparameterization](https://mlsanity.com/paper/2505.22601/) (2025)
- [Unlearning's Blind Spots: Over-Unlearning and Prototypical Relearning Attack](https://mlsanity.com/paper/2506.01318/) (2025)
- [Geometric-disentangelment Unlearning](https://mlsanity.com/paper/2511.17100/) (2025)
- [Evaluating of Machine Unlearning: Robustness Verification Without Prior Modifications](https://mlsanity.com/paper/2410.10120/) (2024)
- [Selective, Controlled and Domain-Agnostic Unlearning in Pretrained CLIP: A Training- and Data-Free Approach](https://mlsanity.com/paper/2512.14113/) (2025)
- [KUDA: Knowledge Unlearning by Deviating Representation for Large Language Models](https://mlsanity.com/paper/2602.19275/) (2026)
- [Recalling The Forgotten Class Memberships: Unlearned Models Can Be Noisy Labelers to Leak Privacy](https://mlsanity.com/paper/2506.19486/) (2025)
- [Zero-Shot Machine Unlearning with Proxy Adversarial Data Generation](https://mlsanity.com/paper/2507.21738/) (2025)
- [Soft Weighted Machine Unlearning](https://mlsanity.com/paper/2505.18783/) (2025)
- [COLUR: Confidence-Oriented Learning, Unlearning and Relearning with Noisy-Label Data for Model Restoration and Refinement](https://mlsanity.com/paper/2506.19496/) (2025)
- [FedShard: Federated Unlearning with Efficiency Fairness and Performance Fairness](https://mlsanity.com/paper/2508.09866/) (2025)
- [Controllable Machine Unlearning via Gradient Pivoting](https://mlsanity.com/paper/2510.19226/) (2025)
- [Retain-Neutral Surrogates for Min-Max Unlearning](https://mlsanity.com/paper/2605.05871/) (2026)
- [Spectral Saliency for Machine Unlearning](https://mlsanity.com/paper/2608.15548/) (2026)
- [Unmerge: Efficient Machine Unlearning via Task Arithmetic](https://mlsanity.com/paper/2609.38895/) (2026)

## Abstract (arXiv)

Machine unlearning aims to enable models to forget specific data instances when receiving deletion requests. Current research centres on efficient unlearning to erase the influence of data from the model and neglects the subsequent impacts on the remaining data. Consequently, existing unlearning algorithms degrade the model's performance after unlearning, known as textitover-unlearning. This paper addresses this critical yet under-explored issue by introducing machine underlineUnlearning via underlineNull underlineSpace underlineCalibration (UNSC), which can accurately unlearn target samples without over-unlearning. On the contrary, by calibrating the decision space during unlearning, UNSC can significantly improve the model's performance on the remaining samples. In particular, our approach hinges on confining the unlearning process to a specified null space tailored to the remaining samples, which is augmented by strategically pseudo-labeling the unlearning samples. Comparative analyses against several established baselines affirm the superiority of our approach. Code is released at this hrefhttps://github.com/HQC-ML/Machine-Unlearning-via-Null-Space-CalibrationURL.