# DeepObliviate: A Powerful Charm for Erasing Data Residual Memory in Deep Neural Networks

arXiv: https://arxiv.org/abs/2105.06209 · HTML: https://mlsanity.com/paper/2105.06209/

## Key facts

- Cited by 19 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 59 references that are in the map.
- First posted on arXiv 13 May 2021.

## 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)
- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [Very Deep Convolutional Networks for Large-Scale Image Recognition](https://mlsanity.com/paper/1409.1556/) (2014)
- [ImageNet Large Scale Visual Recognition Challenge](https://mlsanity.com/paper/1409.0575/) (2014)
- [Going Deeper with Convolutions](https://mlsanity.com/paper/1409.4842/) (2014)
- [Deep Learning with Differential Privacy](https://mlsanity.com/paper/1607.00133/) (2016)
- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Understanding Black-box Predictions via Influence Functions](https://mlsanity.com/paper/1703.04730/) (2017)
- [Machine Unlearning](https://mlsanity.com/paper/1912.03817/) (2019)
- [A Closer Look at Memorization in Deep Networks](https://mlsanity.com/paper/1706.05394/) (2017)
- [The Secret Sharer: Evaluating and Testing Unintended Memorization in Neural Networks](https://mlsanity.com/paper/1802.08232/) (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)
- [Poison Frogs! Targeted Clean-Label Poisoning Attacks on Neural Networks](https://mlsanity.com/paper/1804.00792/) (2018)
- [Making AI Forget You: Data Deletion in Machine Learning](https://mlsanity.com/paper/1907.05012/) (2019)
- [Manipulating Machine Learning: Poisoning Attacks and Countermeasures for Regression Learning](https://mlsanity.com/paper/1804.00308/) (2018)
- [DeltaGrad: Rapid retraining of machine learning models](https://mlsanity.com/paper/2006.14755/) (2020)
- [Machine Unlearning: Linear Filtration for Logit-based Classifiers](https://mlsanity.com/paper/2002.02730/) (2020)
- [Characterizing Concept Drift](https://mlsanity.com/paper/1511.03816/) (2015)
- [Formalizing Data Deletion in the Context of the Right to be Forgotten](https://mlsanity.com/paper/2002.10635/) (2020)
- [Towards Probabilistic Verification of Machine Unlearning](https://mlsanity.com/paper/2003.04247/) (2020)
- [Data Poisoning Attacks against Online Learning](https://mlsanity.com/paper/1808.08994/) (2018)

## Built on by (most cited first, 19 of 19)

- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [Towards Adversarial Evaluations for Inexact Machine Unlearning](https://mlsanity.com/paper/2201.06640/) (2022)
- [Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomy](https://mlsanity.com/paper/2305.06360/) (2023)
- [VeriFi: Towards Verifiable Federated Unlearning](https://mlsanity.com/paper/2205.12709/) (2022)
- [GNNDelete: A General Strategy for Unlearning in Graph Neural Networks](https://mlsanity.com/paper/2302.13406/) (2023)
- [A Review on Machine Unlearning](https://mlsanity.com/paper/2411.11315/) (2024)
- [Corrective Machine Unlearning](https://mlsanity.com/paper/2402.14015/) (2024)
- [Efficiently Forgetting What You Have Learned in Graph Representation Learning via Projection](https://mlsanity.com/paper/2302.08990/) (2023)
- [Machine Unlearning: A Survey](https://mlsanity.com/paper/2306.03558/) (2023)
- [An Introduction to Machine Unlearning](https://mlsanity.com/paper/2209.00939/) (2022)
- [Recommendation Unlearning via Matrix Correction](https://mlsanity.com/paper/2307.15960/) (2023)
- [A Reliable Cryptographic Framework for Empirical Machine Unlearning Evaluation](https://mlsanity.com/paper/2404.11577/) (2024)
- [Distilled Datamodel with Reverse Gradient Matching](https://mlsanity.com/paper/2404.14006/) (2024)
- [Learning to Forget using Hypernetworks](https://mlsanity.com/paper/2412.00761/) (2024)
- ["Forgetting" in Machine Learning and Beyond: A Survey](https://mlsanity.com/paper/2405.20620/) (2024)
- [Survey of Security and Data Attacks on Machine Unlearning In Financial and E-Commerce](https://mlsanity.com/paper/2410.00055/) (2024)
- [Review of Digital Asset Development with Graph Neural Network Unlearning](https://mlsanity.com/paper/2409.18455/) (2024)
- [Prototype Guided Backdoor Defense](https://mlsanity.com/paper/2503.20925/) (2025)
- [Federated Unlearning in the Wild: Rethinking Fairness and Data Discrepancy](https://mlsanity.com/paper/2510.07022/) (2025)

## Abstract (arXiv)

Machine unlearning has great significance in guaranteeing model security and protecting user privacy. Additionally, many legal provisions clearly stipulate that users have the right to demand model providers to delete their own data from training set, that is, the right to be forgotten. The naive way of unlearning data is to retrain the model without it from scratch, which becomes extremely time and resource consuming at the modern scale of deep neural networks. Other unlearning approaches by refactoring model or training data struggle to gain a balance between overhead and model usability. In this paper, we propose an approach, dubbed as DeepObliviate, to implement machine unlearning efficiently, without modifying the normal training mode. Our approach improves the original training process by storing intermediate models on the hard disk. Given a data point to unlearn, we first quantify its temporal residual memory left in stored models. The influenced models will be retrained and we decide when to terminate the retraining based on the trend of residual memory on-the-fly. Last, we stitch an unlearned model by combining the retrained models and uninfluenced models. We extensively evaluate our approach on five datasets and deep learning models. Compared to the method of retraining from scratch, our approach can achieve 99.0%, 95.0%, 91.9%, 96.7%, 74.1% accuracy rates and 66.7×, 75.0×, 33.3×, 29.4×, 13.7× speedups on the MNIST, SVHN, CIFAR-10, Purchase, and ImageNet datasets, respectively. Compared to the state-of-the-art unlearning approach, we improve 5.8% accuracy, 32.5× prediction speedup, and reach a comparable retrain speedup under identical settings on average on these datasets. Additionally, DeepObliviate can also pass the backdoor-based unlearning verification.