# LoTUS: Large-Scale Machine Unlearning with a Taste of Uncertainty

arXiv: https://arxiv.org/abs/2503.18314 · HTML: https://mlsanity.com/paper/2503.18314/

## Key facts

- Cited by 13 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 39 references that are in the map.
- First posted on arXiv 24 Mar 2025.

## 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)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [MINE: Mutual Information Neural Estimation](https://mlsanity.com/paper/1801.04062/) (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)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [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)
- [Fast Machine Unlearning Without Retraining Through Selective Synaptic Dampening](https://mlsanity.com/paper/2308.07707/) (2023)
- [Selective Amnesia: A Continual Learning Approach to Forgetting in Deep Generative Models](https://mlsanity.com/paper/2305.10120/) (2023)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images](https://mlsanity.com/paper/2303.14126/) (2023)
- [Fast Model Debias with Machine Unlearning](https://mlsanity.com/paper/2310.12560/) (2023)
- [Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers](https://mlsanity.com/paper/2301.11578/) (2023)
- [Are we making progress in unlearning? Findings from the first NeurIPS unlearning competition](https://mlsanity.com/paper/2406.09073/) (2024)
- [Towards Machine Unlearning Benchmarks: Forgetting the Personal Identities in Facial Recognition Systems](https://mlsanity.com/paper/2311.02240/) (2023)
- [CPR: Retrieval Augmented Generation for Copyright Protection](https://mlsanity.com/paper/2403.18920/) (2024)
- [Leave-one-out Distinguishability in Machine Learning](https://mlsanity.com/paper/2309.17310/) (2023)
- [Generative Unlearning for Any Identity](https://mlsanity.com/paper/2405.09879/) (2024)
- [Potion: Towards Poison Unlearning](https://mlsanity.com/paper/2406.09173/) (2024)

## Built on by (most cited first, 13 of 13)

- [VLA-Forget: Vision-Language-Action Unlearning for Embodied Foundation Models](https://mlsanity.com/paper/2604.03956/) (2026)
- [RAZOR: Ratio-Aware Layer Editing for Targeted Unlearning in Vision Transformers and Diffusion Models](https://mlsanity.com/paper/2603.14819/) (2026)
- [The Right to be Forgotten in Pruning: Unveil Machine Unlearning on Sparse Models](https://mlsanity.com/paper/2507.18725/) (2025)
- [Evaluating the Defense Potential of Machine Unlearning against Membership Inference Attacks](https://mlsanity.com/paper/2508.16150/) (2025)
- [A Unified Framework for Diffusion Model Unlearning with f-Divergence](https://mlsanity.com/paper/2509.21167/) (2025)
- [IMU: Influence-guided Machine Unlearning](https://mlsanity.com/paper/2508.01620/) (2025)
- [Erased, but Not Gone: Output Forgetting Is Not True Forgetting](https://mlsanity.com/paper/2606.25001/) (2026)
- [Unleashing Uncertainty: Efficient Machine Unlearning for Generative AI](https://mlsanity.com/paper/2508.20773/) (2025)
- [Stake the Points: Structure-Faithful Instance Unlearning](https://mlsanity.com/paper/2603.12915/) (2026)
- [BARRIER: Bounded Activation Regions for Robust Information Erasure](https://mlsanity.com/paper/2605.15737/) (2026)
- [Interference-Aware Multi-Task Unlearning](https://mlsanity.com/paper/2605.19042/) (2026)
- [SPACE: Source-free Proxy Anchor Concept Erasure for MLLMs](https://mlsanity.com/paper/2606.09868/) (2026)
- [IREU: Identity-Related Encoder-Only Unlearning for Customized Portrait Generation](https://mlsanity.com/paper/2606.29880/) (2026)

## Abstract (arXiv)

We present LoTUS, a novel Machine Unlearning (MU) method that eliminates the influence of training samples from pre-trained models, avoiding retraining from scratch. LoTUS smooths the prediction probabilities of the model up to an information-theoretic bound, mitigating its over-confidence stemming from data memorization. We evaluate LoTUS on Transformer and ResNet18 models against eight baselines across five public datasets. Beyond established MU benchmarks, we evaluate unlearning on ImageNet1k, a large-scale dataset, where retraining is impractical, simulating real-world conditions. Moreover, we introduce the novel Retrain-Free Jensen-Shannon Divergence (RF-JSD) metric to enable evaluation under real-world conditions. The experimental results show that LoTUS outperforms state-of-the-art methods in terms of both efficiency and effectiveness. Code: https://github.com/cspartalis/LoTUS.