# Mixed-Privacy Forgetting in Deep Networks

arXiv: https://arxiv.org/abs/2012.13431 · HTML: https://mlsanity.com/paper/2012.13431/

## Key facts

- Cited by 163 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Dec 2020.

## Built on by (most cited first, 30 of 163)

- [A Comprehensive Survey of Continual Learning: Theory, Method and Application](https://mlsanity.com/paper/2302.00487/) (2023)
- [Remember What You Want to Forget: Algorithms for Machine Unlearning](https://mlsanity.com/paper/2103.03279/) (2021)
- [Ablating Concepts in Text-to-Image Diffusion Models](https://mlsanity.com/paper/2303.13516/) (2023)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Towards Unbounded Machine Unlearning](https://mlsanity.com/paper/2302.09880/) (2023)
- [Machine Unlearning of Features and Labels](https://mlsanity.com/paper/2108.11577/) (2021)
- [In-Context Unlearning: Language Models as Few Shot Unlearners](https://mlsanity.com/paper/2310.07579/) (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)
- [Adaptive Machine Unlearning](https://mlsanity.com/paper/2106.04378/) (2021)
- [Zero-Shot Machine Unlearning](https://mlsanity.com/paper/2201.05629/) (2022)
- [Continual Learning and Private Unlearning](https://mlsanity.com/paper/2203.12817/) (2022)
- [Measuring Forgetting of Memorized Training Examples](https://mlsanity.com/paper/2207.00099/) (2022)
- [Federated Unlearning via Class-Discriminative Pruning](https://mlsanity.com/paper/2110.11794/) (2021)
- [Machine Unlearning: Solutions and Challenges](https://mlsanity.com/paper/2308.07061/) (2023)
- [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)
- [Inexact Unlearning Needs More Careful Evaluations to Avoid a False Sense of Privacy](https://mlsanity.com/paper/2403.01218/) (2024)
- [Scissorhands: Scrub Data Influence via Connection Sensitivity in Networks](https://mlsanity.com/paper/2401.06187/) (2024)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [ASIF: Coupled Data Turns Unimodal Models to Multimodal Without Training](https://mlsanity.com/paper/2210.01738/) (2022)
- [Survey: Leakage and Privacy at Inference Time](https://mlsanity.com/paper/2107.01614/) (2021)
- [Hidden Poison: Machine Unlearning Enables Camouflaged Poisoning Attacks](https://mlsanity.com/paper/2212.10717/) (2022)
- [GNNDelete: A General Strategy for Unlearning in Graph Neural Networks](https://mlsanity.com/paper/2302.13406/) (2023)
- [Certifiable Machine Unlearning for Linear Models](https://mlsanity.com/paper/2106.15093/) (2021)
- [Evaluating Machine Unlearning via Epistemic Uncertainty](https://mlsanity.com/paper/2208.10836/) (2022)
- [Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection](https://mlsanity.com/paper/2312.04095/) (2023)
- [Machine Unlearning: A Comprehensive Survey](https://mlsanity.com/paper/2405.07406/) (2024)
- [Deep Regression Unlearning](https://mlsanity.com/paper/2210.08196/) (2022)

## Abstract (arXiv)

We show that the influence of a subset of the training samples can be removed -- or "forgotten" -- from the weights of a network trained on large-scale image classification tasks, and we provide strong computable bounds on the amount of remaining information after forgetting. Inspired by real-world applications of forgetting techniques, we introduce a novel notion of forgetting in mixed-privacy setting, where we know that a "core" subset of the training samples does not need to be forgotten. While this variation of the problem is conceptually simple, we show that working in this setting significantly improves the accuracy and guarantees of forgetting methods applied to vision classification tasks. Moreover, our method allows efficient removal of all information contained in non-core data by simply setting to zero a subset of the weights with minimal loss in performance. We achieve these results by replacing a standard deep network with a suitable linear approximation. With opportune changes to the network architecture and training procedure, we show that such linear approximation achieves comparable performance to the original network and that the forgetting problem becomes quadratic and can be solved efficiently even for large models. Unlike previous forgetting methods on deep networks, ours can achieve close to the state-of-the-art accuracy on large scale vision tasks. In particular, we show that our method allows forgetting without having to trade off the model accuracy.