# System-Aware Unlearning Algorithms: Use Lesser, Forget Faster

arXiv: https://arxiv.org/abs/2506.06073 · HTML: https://mlsanity.com/paper/2506.06073/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 30 of its 54 references that are in the map.
- First posted on arXiv 6 Jun 2025.

## Placed in

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

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

- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Probing Classifiers: Promises, Shortcomings, and Advances](https://mlsanity.com/paper/2102.12452/) (2021)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Do Better ImageNet Models Transfer Better?](https://mlsanity.com/paper/1805.08974/) (2018)
- [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)
- [Knowledge Unlearning for Mitigating Privacy Risks in Language Models](https://mlsanity.com/paper/2210.01504/) (2022)
- [A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Ugly](https://mlsanity.com/paper/2312.02003/) (2023)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Descent-to-Delete: Gradient-Based Methods for Machine Unlearning](https://mlsanity.com/paper/2007.02923/) (2020)
- [Approximate Data Deletion from Machine Learning Models](https://mlsanity.com/paper/2002.10077/) (2020)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy](https://mlsanity.com/paper/2403.01218/) (2024)
- [Instance-Dependent Complexity of Contextual Bandits and Reinforcement Learning: A Disagreement-Based Perspective](https://mlsanity.com/paper/2010.03104/) (2020)
- [Forget Unlearning: Towards True Data-Deletion in Machine Learning](https://mlsanity.com/paper/2210.08911/) (2022)
- [Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning](https://mlsanity.com/paper/2401.10371/) (2024)
- [Differential Privacy as a Mutual Information Constraint](https://mlsanity.com/paper/1608.03677/) (2016)
- [Learning with Square Loss: Localization through Offset Rademacher Complexity](https://mlsanity.com/paper/1502.06134/) (2015)
- [Machine Unlearning Fails to Remove Data Poisoning Attacks](https://mlsanity.com/paper/2406.17216/) (2024)
- [Stable Sample Compression Schemes: New Applications and an Optimal SVM Margin Bound](https://mlsanity.com/paper/2011.04586/) (2020)
- [Towards Scalable Exact Machine Unlearning Using Parameter-Efficient Fine-Tuning](https://mlsanity.com/paper/2406.16257/) (2024)
- [Avoiding Copyright Infringement via Large Language Model Unlearning](https://mlsanity.com/paper/2406.10952/) (2024)
- [Efficient Active Learning with Abstention](https://mlsanity.com/paper/2204.00043/) (2022)
- [Is Retain Set All You Need in Machine Unlearning? Restoring Performance of Unlearned Models with Out-Of-Distribution Images](https://mlsanity.com/paper/2404.12922/) (2024)
- [Fast Rates in Pool-Based Batch Active Learning](https://mlsanity.com/paper/2202.05448/) (2022)
- [Selective Sampling and Imitation Learning via Online Regression](https://mlsanity.com/paper/2307.04998/) (2023)
- [Ticketed Learning-Unlearning Schemes](https://mlsanity.com/paper/2306.15744/) (2023)
- [The Limits of Pan Privacy and Shuffle Privacy for Learning and Estimation](https://mlsanity.com/paper/2009.08000/) (2020)

## Built on by (most cited first, 4 of 4)

- [Unlearning at Scale: State-Exact Trace-Preserving Deletion in Billion-Parameter Language Models](https://mlsanity.com/paper/2508.12220/) (2025)
- [Temper-Then-Tilt: Principled Unlearning for Generative Models through Tempering and Classifier Guidance](https://mlsanity.com/paper/2602.10217/) (2026)
- [Certified Per-Instance Unlearning Using Individual Sensitivity Bounds](https://mlsanity.com/paper/2602.15602/) (2026)
- [One-Step Curvature Probes Miss the Fitting Operator: Retained Capacity and Terminal Null-Space Correction for Continual Learning](https://mlsanity.com/paper/2610.03952/) (2026)

## Abstract (arXiv)

Machine unlearning addresses the problem of updating a machine learning model/system trained on a dataset S so that the influence of a set of deletion requests U subseteq S on the unlearned model is minimized. The gold standard definition of unlearning demands that the updated model, after deletion, be nearly identical to the model obtained by retraining. This definition is designed for a worst-case attacker (one who can recover not only the unlearned model but also the remaining data samples, i.e., S setminus U). Such a stringent definition has made developing efficient unlearning algorithms challenging. However, such strong attackers are also unrealistic. In this work, we propose a new definition, system-aware unlearning, which aims to provide unlearning guarantees against an attacker that can at best only gain access to the data stored in the system for learning/unlearning requests and not all of Ssetminus U. With this new definition, we use the simple intuition that if a system can store less to make its learning/unlearning updates, it can be more secure and update more efficiently against a system-aware attacker. Towards that end, we present an exact system-aware unlearning algorithm for linear classification using a selective sampling-based approach, and we generalize the method for classification with general function classes. We theoretically analyze the tradeoffs between deletion capacity, accuracy, memory, and computation time.