# DeepClean: Machine Unlearning on the Cheap by Resetting Privacy Sensitive Weights using the Fisher Diagonal

arXiv: https://arxiv.org/abs/2311.10448 · HTML: https://mlsanity.com/paper/2311.10448/

## 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.
- Builds on 20 of its 33 references that are in the map.
- First posted on arXiv 17 Nov 2023.

## Placed in

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

## Builds on (most cited first, 20 of 20)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [Overcoming catastrophic forgetting in neural networks](https://mlsanity.com/paper/1612.00796/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Fast Yet Effective Machine Unlearning](https://mlsanity.com/paper/2111.08947/) (2021)
- [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://mlsanity.com/paper/2205.08096/) (2022)
- [On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning](https://mlsanity.com/paper/2110.11891/) (2021)
- [Mixed-Privacy Forgetting in Deep Networks](https://mlsanity.com/paper/2012.13431/) (2020)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [Deep Unlearning via Randomized Conditionally Independent Hessians](https://mlsanity.com/paper/2204.07655/) (2022)
- [Deep Regression Unlearning](https://mlsanity.com/paper/2210.08196/) (2022)
- [Efficient Attribute Unlearning: Towards Selective Removal of Input Attributes from Feature Representations](https://mlsanity.com/paper/2202.13295/) (2022)
- [An Introduction to Machine Unlearning](https://mlsanity.com/paper/2209.00939/) (2022)
- [Unlearning with Fisher Masking](https://mlsanity.com/paper/2310.05331/) (2023)
- [Generative Extraction of Audio Classifiers for Speaker Identification](https://mlsanity.com/paper/2207.12816/) (2022)

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

- [Machine Unlearning under Retain-Forget Entanglement](https://mlsanity.com/paper/2603.26569/) (2026)
- [Forget-MI: Machine Unlearning for Forgetting Multimodal Information in Healthcare Settings](https://mlsanity.com/paper/2506.23145/) (2025)
- [Module-Aware Parameter-Efficient Machine Unlearning on Transformers](https://mlsanity.com/paper/2508.17233/) (2025)
- [Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometrics](https://mlsanity.com/paper/2507.22208/) (2025)
- [Remembering Everything Makes You Vulnerable: A Limelight on Machine Unlearning for Personalized Healthcare Sector](https://mlsanity.com/paper/2407.04589/) (2024)
- [FiCABU: A Fisher-Based, Context-Adaptive Machine Unlearning Processor for Edge AI](https://mlsanity.com/paper/2511.05605/) (2025)
- [RapidUn: Influence-Driven Parameter Reweighting for Efficient Large Language Model Unlearning](https://mlsanity.com/paper/2512.04457/) (2025)

## Abstract (arXiv)

Machine learning models trained on sensitive or private data can inadvertently memorize and leak that information. Machine unlearning seeks to retroactively remove such details from model weights to protect privacy. We contribute a lightweight unlearning algorithm that leverages the Fisher Information Matrix (FIM) for selective forgetting. Prior work in this area requires full retraining or large matrix inversions, which are computationally expensive. Our key insight is that the diagonal elements of the FIM, which measure the sensitivity of log-likelihood to changes in weights, contain sufficient information for effective forgetting. Specifically, we compute the FIM diagonal over two subsets -- the data to retain and forget -- for all trainable weights. This diagonal representation approximates the complete FIM while dramatically reducing computation. We then use it to selectively update weights to maximize forgetting of the sensitive subset while minimizing impact on the retained subset. Experiments show that our algorithm can successfully forget any randomly selected subsets of training data across neural network architectures. By leveraging the FIM diagonal, our approach provides an interpretable, lightweight, and efficient solution for machine unlearning with practical privacy benefits.