# Accurate Forgetting for All-in-One Image Restoration Model

arXiv: https://arxiv.org/abs/2409.00685 · HTML: https://mlsanity.com/paper/2409.00685/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 25 of its 39 references that are in the map.
- First posted on arXiv 1 Sep 2024.

## Placed in

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

## Builds on (most cited first, 25 of 25)

- [Towards Deep Learning Models Resistant to Adversarial Attacks](https://mlsanity.com/paper/1706.06083/) (2017)
- [Intriguing properties of neural networks](https://mlsanity.com/paper/1312.6199/) (2013)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [Adversarial Examples Are Not Bugs, They Are Features](https://mlsanity.com/paper/1905.02175/) (2019)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (2018)
- [Lifelong Learning with Dynamically Expandable Networks](https://mlsanity.com/paper/1708.01547/) (2017)
- [Square Attack: a query-efficient black-box adversarial attack via random search](https://mlsanity.com/paper/1912.00049/) (2019)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Benchmarking Single Image Dehazing and Beyond](https://mlsanity.com/paper/1712.04143/) (2017)
- [Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attack](https://mlsanity.com/paper/1907.02044/) (2019)
- [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)
- [Mixed-Privacy Forgetting in Deep Networks](https://mlsanity.com/paper/2012.13431/) (2020)
- [Zero-Shot Machine Unlearning](https://mlsanity.com/paper/2201.05629/) (2022)
- [AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation](https://mlsanity.com/paper/2403.14614/) (2024)
- [AutoDIR: Automatic All-in-One Image Restoration with Latent Diffusion](https://mlsanity.com/paper/2310.10123/) (2023)
- [Embedding Fourier for Ultra-High-Definition Low-Light Image Enhancement](https://mlsanity.com/paper/2302.11831/) (2023)
- [A General Decoupled Learning Framework for Parameterized Image Operators](https://mlsanity.com/paper/1907.05852/) (2019)
- [Multimodal Prompt Perceiver: Empower Adaptiveness, Generalizability and Fidelity for All-in-One Image Restoration](https://mlsanity.com/paper/2312.02918/) (2023)
- [Machine Unlearning for Image-to-Image Generative Models](https://mlsanity.com/paper/2402.00351/) (2024)
- [Certified Graph Unlearning](https://mlsanity.com/paper/2206.09140/) (2022)
- [Language-driven All-in-one Adverse Weather Removal](https://mlsanity.com/paper/2312.01381/) (2023)
- [Deep Regression Unlearning](https://mlsanity.com/paper/2210.08196/) (2022)
- [Textual Prompt Guided Image Restoration](https://mlsanity.com/paper/2312.06162/) (2023)

## Built on by (most cited first, 1 of 1)

- [A Survey on All-in-One Image Restoration: Taxonomy, Evaluation and Future Trends](https://mlsanity.com/paper/2410.15067/) (2024)

## Abstract (arXiv)

Privacy protection has always been an ongoing topic, especially for AI. Currently, a low-cost scheme called Machine Unlearning forgets the private data remembered in the model. Specifically, given a private dataset and a trained neural network, we need to use e.g. pruning, fine-tuning, and gradient ascent to remove the influence of the private dataset on the neural network. Inspired by this, we try to use this concept to bridge the gap between the fields of image restoration and security, creating a new research idea. We propose the scene for the All-In-One model (a neural network that restores a wide range of degraded information), where a given dataset such as haze, or rain, is private and needs to be eliminated from the influence of it on the trained model. Notably, we find great challenges in this task to remove the influence of sensitive data while ensuring that the overall model performance remains robust, which is akin to directing a symphony orchestra without specific instruments while keeping the playing soothing. Here we explore a simple but effective approach: Instance-wise Unlearning through the use of adversarial examples and gradient ascent techniques. Our approach is a low-cost solution compared to the strategy of retraining the model from scratch, where the gradient ascent trick forgets the specified data and the performance of the adversarial sample maintenance model is robust. Through extensive experimentation on two popular unified image restoration models, we show that our approach effectively preserves knowledge of remaining data while unlearning a given degradation type.