# Targeted Unlearning Using Perturbed Sign Gradient Methods With Applications On Medical Images

arXiv: https://arxiv.org/abs/2505.21872 · HTML: https://mlsanity.com/paper/2505.21872/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 32 of its 50 references that are in the map.
- First posted on arXiv 28 May 2025.

## Placed in

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

## Builds on (most cited first, 30 of 32)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [Explaining and Harnessing Adversarial Examples](https://mlsanity.com/paper/1412.6572/) (2014)
- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [Striving for Simplicity: The All Convolutional Net](https://mlsanity.com/paper/1412.6806/) (2014)
- [Membership Inference Attacks From First Principles](https://mlsanity.com/paper/2112.03570/) (2021)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Domain Adaptation for Medical Image Analysis: A Survey](https://mlsanity.com/paper/2102.09508/) (2021)
- [Amnesiac Machine Learning](https://mlsanity.com/paper/2010.10981/) (2020)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [On the Robustness of Vision Transformers to Adversarial Examples](https://mlsanity.com/paper/2104.02610/) (2021)
- [Handbook of Convergence Theorems for (Stochastic) Gradient Methods](https://mlsanity.com/paper/2301.11235/) (2023)
- [Boundary Unlearning](https://mlsanity.com/paper/2303.11570/) (2023)
- [A Convex Relaxation Barrier to Tight Robustness Verification of Neural Networks](https://mlsanity.com/paper/1902.08722/) (2019)
- [On the Adversarial Robustness of Vision Transformers](https://mlsanity.com/paper/2103.15670/) (2021)
- [The rising costs of training frontier AI models](https://mlsanity.com/paper/2405.21015/) (2024)
- [Towards Adversarial Evaluations for Inexact Machine Unlearning](https://mlsanity.com/paper/2201.06640/) (2022)
- [Deep Unlearning via Randomized Conditionally Independent Hessians](https://mlsanity.com/paper/2204.07655/) (2022)
- [Continual Learning: Applications and the Road Forward](https://mlsanity.com/paper/2311.11908/) (2023)
- [Stochastic Sign Descent Methods: New Algorithms and Better Theory](https://mlsanity.com/paper/1905.12938/) (2019)
- [Langevin Unlearning: A New Perspective of Noisy Gradient Descent for Machine Unlearning](https://mlsanity.com/paper/2401.10371/) (2024)
- [Machine Unlearning: A Comprehensive Survey](https://mlsanity.com/paper/2405.07406/) (2024)
- [G1020: A Benchmark Retinal Fundus Image Dataset for Computer-Aided Glaucoma Detection](https://mlsanity.com/paper/2006.09158/) (2020)
- [SSSE: Efficiently Erasing Samples from Trained Machine Learning Models](https://mlsanity.com/paper/2107.03860/) (2021)
- [Deep learning for unsupervised domain adaptation in medical imaging: Recent advancements and future perspectives](https://mlsanity.com/paper/2308.01265/) (2023)
- [Breaking the Trilemma of Privacy, Utility, Efficiency via Controllable Machine Unlearning](https://mlsanity.com/paper/2310.18574/) (2023)
- [A Survey on Machine Unlearning: Techniques and New Emerged Privacy Risks](https://mlsanity.com/paper/2406.06186/) (2024)
- [I-ODA, Real-World Multi-modal Longitudinal Data for OphthalmicApplications](https://mlsanity.com/paper/2104.02609/) (2021)
- [Erase to Enhance: Data-Efficient Machine Unlearning in MRI Reconstruction](https://mlsanity.com/paper/2405.15517/) (2024)

## Abstract (arXiv)

Machine unlearning aims to remove the influence of specific training samples from a trained model without full retraining. While prior work has largely focused on privacy-motivated settings, we recast unlearning as a general-purpose tool for post-deployment model revision. Specifically, we focus on utilizing unlearning in clinical contexts where data shifts, device deprecation, and policy changes are common. To this end, we propose a bilevel optimization formulation of boundary-based unlearning that can be solved using iterative algorithms. We provide convergence guarantees when first-order algorithms are used to unlearn. Our method introduces tunable loss design for controlling the forgetting-retention tradeoff and supports novel model composition strategies that merge the strengths of distinct unlearning runs. Across benchmark and real-world clinical imaging datasets, our approach outperforms baselines on both forgetting and retention metrics, including scenarios involving imaging devices and anatomical outliers. This work establishes machine unlearning as a modular, practical alternative to retraining for real-world model maintenance in clinical applications.