# Redirection for Erasing Memory (REM): Towards a universal unlearning method for corrupted data

arXiv: https://arxiv.org/abs/2505.17730 · HTML: https://mlsanity.com/paper/2505.17730/

## 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 27 of its 31 references that are in the map.
- First posted on arXiv 23 May 2025.

## Placed in

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

## Builds on (most cited first, 27 of 27)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Negative Preference Optimization: From Catastrophic Collapse to Effective Unlearning](https://mlsanity.com/paper/2404.05868/) (2024)
- [What Neural Networks Memorize and Why: Discovering the Long Tail via Influence Estimation](https://mlsanity.com/paper/2008.03703/) (2020)
- [Does Learning Require Memorization? A Short Tale about a Long Tail](https://mlsanity.com/paper/1906.05271/) (2019)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [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)
- [Poisoning Web-Scale Training Datasets is Practical](https://mlsanity.com/paper/2302.10149/) (2023)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [Can Bad Teaching Induce Forgetting? Unlearning in Deep Networks using an Incompetent Teacher](https://mlsanity.com/paper/2205.08096/) (2022)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Characterizing Structural Regularities of Labeled Data in Overparameterized Models](https://mlsanity.com/paper/2002.03206/) (2020)
- [What makes unlearning hard and what to do about it](https://mlsanity.com/paper/2406.01257/) (2024)
- [Towards Adversarial Evaluations for Inexact Machine Unlearning](https://mlsanity.com/paper/2201.06640/) (2022)
- [Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy](https://mlsanity.com/paper/2403.01218/) (2024)
- [Can Neural Network Memorization Be Localized?](https://mlsanity.com/paper/2307.09542/) (2023)
- [Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition](https://mlsanity.com/paper/2406.09073/) (2024)
- [Be like a Goldfish, Don't Memorize! Mitigating Memorization in Generative LLMs](https://mlsanity.com/paper/2406.10209/) (2024)
- [Persistent Pre-Training Poisoning of LLMs](https://mlsanity.com/paper/2410.13722/) (2024)
- [Corrective Machine Unlearning](https://mlsanity.com/paper/2402.14015/) (2024)
- [Repairing Neural Networks by Leaving the Right Past Behind](https://mlsanity.com/paper/2207.04806/) (2022)
- [Potion: Towards Poison Unlearning](https://mlsanity.com/paper/2406.09173/) (2024)
- [Parameter-tuning-free data entry error unlearning with adaptive selective synaptic dampening](https://mlsanity.com/paper/2402.10098/) (2024)
- [Improved Localized Machine Unlearning Through the Lens of Memorization](https://mlsanity.com/paper/2412.02432/) (2024)

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

- [Beyond Data Filtering: Knowledge Localization for Capability Removal in LLMs](https://mlsanity.com/paper/2512.05648/) (2025)
- [Is your algorithm unlearning or untraining?](https://mlsanity.com/paper/2604.07962/) (2026)
- [LLM Unlearning on Noisy Forget Sets: A Study of Incomplete, Rewritten, and Watermarked Data](https://mlsanity.com/paper/2510.09007/) (2025)
- [Position: Capability Control Should be a Separate Goal From Alignment](https://mlsanity.com/paper/2602.05164/) (2026)
- [RippleBench: Capturing Ripple Effects Using Existing Knowledge Repositories](https://mlsanity.com/paper/2512.04144/) (2025)
- [Subtract the Corruption: Training-Data-Free Corrective Machine Unlearning using Task Arithmetic](https://mlsanity.com/paper/2511.18660/) (2025)
- [Variance-Reduced (varepsilon,δ)-Unlearning using Forget Set Gradients](https://mlsanity.com/paper/2602.14938/) (2026)

## Abstract (arXiv)

Machine unlearning is studied for a multitude of tasks, but specialization of unlearning methods to particular tasks has made their systematic comparison challenging. To address this issue, we propose a conceptual space to characterize diverse corrupted data unlearning tasks in vision classifiers. This space is described by two dimensions, the discovery rate (the fraction of the corrupted data that are known at unlearning time) and the statistical regularity of the corrupted data (from random exemplars to shared concepts). Methods proposed previously have been targeted at portions of this space and-we show-fail predictably outside these regions. We propose a novel method, Redirection for Erasing Memory (REM), whose key feature is that corrupted data are redirected to dedicated neurons introduced at unlearning time and then discarded or deactivated to suppress the influence of corrupted data. REM performs strongly across the space of tasks, in contrast to prior SOTA methods that fail outside the regions for which they were designed.