mlsanityData to 7 Oct 2026

Lightweight machine unlearning in neural network

arXiv 2111.05528 ↗First posted 10 Nov 2021cs.LG cs.AIcited by 4

On the map: LLM safety and security → Machine unlearning

Abstract (arXiv)

In recent years, machine learning neural network has penetrated deeply into people's life. As the price of convenience, people's private information also has the risk of disclosure. The "right to be forgotten" was introduced in a timely manner, stipulating that individuals have the right to withdraw their consent from personal information processing activities based on their consent. To solve this problem, machine unlearning is proposed, which allows the model to erase all memory of private information. Previous studies, including retraining and incremental learning to update models, often take up extra storage space or are difficult to apply to neural networks. Our method only needs to make a small perturbation of the weight of the target model and make it iterate in the direction of the model trained with the remaining data subset until the contribution of the unlearning data to the model is completely eliminated. In this paper, experiments on five datasets prove the effectiveness of our method for machine unlearning, and our method is 15 times faster than retraining.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Placed in Machine unlearning, one of 12 directions in LLM safety and security. Builds on 22 of its 35 references that are in the map. First posted on arXiv 10 Nov 2021.

Builds on

22 of 35 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,283
  4. 2016Membership Inference Attacks against Machine Learning Modelscited by 2,221
  5. 2017BadNets: Identifying Vulnerabilities in the Machine Learning Model Supply Chaincited by 1,052
  6. 2019Machine Unlearningcited by 1,020
  7. 2019Deep Leakage from Gradientscited by 1,004
  8. 2019Certified Data Removal from Machine Learning Modelscited by 512
  9. 2018ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Modelscited by 475
  10. 2019Making AI Forget You: Data Deletion in Machine Learningcited by 447
  11. 2020Reflection Backdoor: A Natural Backdoor Attack on Deep Neural Networkscited by 341
  12. 2020Descent-to-Delete: Gradient-Based Methods for Machine Unlearningcited by 303
10 more
  1. 2016NIPS 2016 Tutorial: Generative Adversarial Networkscited by 284
  2. 2020Approximate Data Deletion from Machine Learning Modelscited by 250
  3. 2019MemGuard: Defending against Black-Box Membership Inference Attacks via Adversarial Examplescited by 183
  4. 2020Variational Bayesian Unlearningcited by 114
  5. 2020An Embarrassingly Simple Approach for Trojan Attack in Deep Neural Networkscited by 92
  6. 2020Machine Unlearning: Linear Filtration for Logit-based Classifierscited by 89
  7. 2020Radioactive data: tracing through trainingcited by 67
  8. 2020Towards Probabilistic Verification of Machine Unlearningcited by 46
  9. 2020Federated Unlearningcited by 27
  10. 2018Detecting Regions of Maximal Divergence for Spatio-Temporal Anomaly Detectioncited by 18

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 1.

4 papers.

  1. 2023Exploring the Landscape of Machine Unlearning: A Comprehensive Survey and Taxonomycited by 44
  2. 2023GNNDelete: A General Strategy for Unlearning in Graph Neural Networkscited by 43
  3. 2023On the Effectiveness of Unlearning in Session-Based Recommendationcited by 4
  4. 2024Game-Theoretic Machine Unlearning: Mitigating Extra Privacy Leakagecited by 0