Fast Yet Effective Machine Unlearning
Open accessThe DOI matches its Crossref record; 32 of the 32 references it cites were found in a registry or an index.
Abstract
Unlearning the data observed during the training of a machine learning (ML) model is an important task that can play a pivotal role in fortifying the privacy and security of ML-based applications. This article raises the following questions: 1) can we unlearn a single or multiple class(es) of data from an ML model without looking at the full training data even once? and 2) can we make the process of unlearning fast and scalable to large datasets, and generalize it to different deep networks? We introduce a novel machine unlearning framework with error-maximizing noise generation and impair-repair based weight manipulation that offers an efficient solution to the above questions. An error-maximizing noise matrix is learned for the class to be unlearned using the original model. The noise matrix is used to manipulate the model weights to unlearn the targeted class of data. We introduce impair and repair steps for a controlled manipulation of the network weights. In the impair step, the noise matrix along with a very high learning rate is used to induce sharp unlearning in the model. Thereafter, the repair step is used to regain the overall performance. With very few update steps, we show excellent unlearning while substantially retaining the overall model accuracy. Unlearning multiple classes requires a similar number of update steps as for a single class, making our approach scalable to large problems. Our method is quite efficient in comparison to the existing methods, works for multiclass unlearning, does not put any constraints on the original optimization mechanism or network design, and works well in both small and large-scale vision tasks. This work is an important step toward fast and easy implementation of unlearning in deep networks. Source code: https://github.com/vikram2000b/Fast-Machine-Unlearning.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale
Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., et al. (2020) · arXiv · doi:10.48550/arxiv.2010.11929 · Cited by 47,472
MobileNetV2: Inverted Residuals and Linear Bottlenecks
Sandler, M., Howard, A., Zhu, M., Zhmoginov, A., & Chen, L.-C. (2018) · 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition · doi:10.1109/cvpr.2018.00474 · Cited by 28,755
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.74 · Cited by 24,513
Explaining and Harnessing Adversarial Examples
Goodfellow, I. J., Shlens, J., & Szegedy, C. (2014) · arXiv · doi:10.48550/arxiv.1412.6572 · Cited by 10,381
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2014) · Foundations and Trends® in Theoretical Computer Science · doi:10.1561/0400000042 · Cited by 5,557
The Algorithmic Foundations of Differential Privacy
Dwork, C., & Roth, A. (2013) · doi:10.1561/9781601988195 · Cited by 3,856
Striving for Simplicity: The All Convolutional Net
Springenberg, J. T., Dosovitskiy, A., Brox, T., & Riedmiller, M. (2014) · arXiv · doi:10.48550/arxiv.1412.6806 · Cited by 3,447
VGGFace2: A Dataset for Recognising Faces across Pose and Age
Cao, Q., Shen, L., Xie, W., Parkhi, O. M., & Zisserman, A. (2018) · 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018) · doi:10.1109/fg.2018.00020 · Cited by 3,032
The EU General Data Protection Regulation (GDPR)
Voigt, P., & von dem Bussche, A. (2017) · doi:10.1007/978-3-319-57959-7 · Cited by 3,001
Universal Adversarial Perturbations
Moosavi-Dezfooli, S.-M., Fawzi, A., Fawzi, O., & Frossard, P. (2017) · 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2017.17 · Cited by 2,680
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · cited 1×
“Data privacy in machine learning has been extensively studied and various privacy-preserving mechanisms have been presented [1, 36, 42].”
BackgroundUnderstanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · cited 2×
“Estimating the effect of a data sample or a class of data samples on the deep model parameters is a challenging problem [17, 27, 28].”
BackgroundMethodBourtoule, L., Chandrasekaran, V., Choquette-Choo, C. A., Jia, H., Travers, A., Zhang, B., Lie, D., & Papernot, N. (2021) · 2021 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp40001.2021.00019 · Cited by 810 · cited 1×
“Some methods adopt strategic grouping of data in the training procedure and thus enable smooth unlearning by limiting the influence of data points on model learning [4, 46].”
MethodThe Loss Surfaces of Multilayer Networks
Choromanska, A., Henaff, M., Mathieu, M., Arous, G. B., & LeCun, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.0233 · Cited by 733
Towards Making Systems Forget with Machine Unlearning
Cao, Y., & Yang, J. (2015) · 2015 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2015.35 · Cited by 622 · cited 1×
“Machine unlearning was formulated as a data forgetting algorithm in statistical query learning [8].”
BackgroundEternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks
Golatkar, A., Achille, A., & Soatto, S. (2020) · 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr42600.2020.00932 · Cited by 394
Privacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · 2015 53rd Annual Allerton Conference on Communication, Control, and Computing (Allerton) · doi:10.1109/allerton.2015.7447103 · Cited by 223
When Machine Unlearning Jeopardizes Privacy
Chen, M., Zhang, Z., Wang, T., Backes, M., Humbert, M., & Zhang, Y. (2021) · Proceedings of the 2021 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/3460120.3484756 · Cited by 195 · cited 1×
“Some researchers have studied the unintended privacy risks resulting from the existing unlearning methods [34], [35].”
BackgroundMaking AI Forget You: Data Deletion in Machine Learning
Ginart, A., Guan, M. Y., Valiant, G., & Zou, J. (2019) · arXiv · doi:10.48550/arxiv.1907.05012 · Cited by 175 · cited 2×
“The unlearning (also called selective forgetting, data deletion, or scrubbing) solutions presented in the literature are focused on simple learning algorithms such a linear/logistic regression [31], random forests [6], and kmeans clustering [16].”
MethodCertified Data Removal from Machine Learning Models
Guo, C., Goldstein, T., Hannun, A., & van der Maaten, L. (2019) · arXiv · doi:10.48550/arxiv.1911.03030 · Cited by 160 · cited 1×
“[23] give a certified information removal framework based on Newton’s update removal mechanism for convex learning problems.”
MethodMixed-Privacy Forgetting in Deep Networks
Golatkar, A., Achille, A., Ravichandran, A., Polito, M., & Soatto, S. (2021) · 2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr46437.2021.00085 · Cited by 125 · cited 3×
“Some privacy settings [18, 26] allow the user to make a request to forget their data from the already trained model.”
BackgroundGolatkar, A., Achille, A., & Soatto, S. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-58526-6_23 · Cited by 122
Chen, C., Sun, F., Zhang, M., & Ding, B. (2022) · Proceedings of the ACM Web Conference 2022 · doi:10.1145/3485447.3511997 · Cited by 110 · cited 1×
“machine learning [37] and recommendation systems [38] are also explored.”
BackgroundRemember What You Want to Forget: Algorithms for Machine Unlearning
Sekhari, A., Acharya, J., Kamath, G., & Suresh, A. T. (2021) · arXiv · doi:10.48550/arxiv.2103.03279 · Cited by 99
Machine Unlearning for Random Forests
Brophy, J., & Lowd, D. (2020) · arXiv · doi:10.48550/arxiv.2009.05567 · Cited by 70 · cited 1×
“effect on the overall accuracy of the model? These are some of the questions that have been asked and probable solutions have been explored in recent times [3], [4], [5], [6], [7], [8], [9], [10], [11], [12], [13], [14], [15], [16].”
BackgroundGupta, V., Jung, C., Neel, S., Roth, A., Sharifi-Malvajerdi, S., & Waites, C. (2021) · arXiv · doi:10.48550/arxiv.2106.04378 · Cited by 67
Hard to Forget: Poisoning Attacks on Certified Machine Unlearning
Marchant, N. G., Rubinstein, B. I. P., & Alfeld, S. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i7.20736 · Cited by 64 · cited 1×
“Some researchers have studied the unintended privacy risks resulting from the existing unlearning methods [34], [35].”
BackgroundAthena: Probabilistic Verification of Machine Unlearning
Sommer, D. M., Song, L., Wagh, S., & Mittal, P. (2022) · Proceedings on Privacy Enhancing Technologies · doi:10.56553/popets-2022-0072 · Cited by 51
On the Necessity of Auditable Algorithmic Definitions for Machine Unlearning
Thudi, A., Jia, H., Shumailov, I., & Papernot, N. (2021) · arXiv · doi:10.48550/arxiv.2110.11891 · Cited by 48 · cited 1×
“[36] show the difficulty of formally proving the absence of certain data points in the model.”
BackgroundLearning with Selective Forgetting
Shibata, T., Irie, G., Ikami, D., & Mitsuzumi, Y. (2021) · Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2021/137 · Cited by 47 · cited 1×
“Several other notable works include [39], [40], [41], [42].”
BackgroundTowards Probabilistic Verification of Machine Unlearning
Sommer, D. M., Song, L., Wagh, S., & Mittal, P. (2020) · arXiv · doi:10.48550/arxiv.2003.04247 · Cited by 38
Cited by
Chundawat, V. S., Tarun, A. K., Mandal, M., & Kankanhalli, M. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3265506 · Cited by 162
Self-citationXu, H., Zhu, T., Zhang, L., Zhou, W., & Yu, P. S. (2024) · ACM Computing Surveys · doi:10.1145/3603620 · Cited by 164
“[27] evaluated the verifiability through several measurements.”
BackgroundMethodInfluential(2023) · doi:10.18653/v1/2023.emnlp-main.632 · Cited by 115
Editing Large Language Models: Problems, Methods, and Opportunities
Yao, Y., Wang, P., Tian, B., Cheng, S., Li, Z., Deng, S., Chen, H., & Zhang, N. (2023) · arXiv · doi:10.48550/arxiv.2305.13172 · Cited by 115
“Moreover, it’s vital for models to forget sensitive knowledge, aligning with machine unlearning concepts (Hase et al., 2023; Wu et al., 2022; Tarun et al., 2021; Gandikota et al., 2023).”
BackgroundA Survey of Machine Unlearning
Nguyen, T. T., Huynh, T. T., Ren, Z., Nguyen, P. L., Liew, A. W.-C., Yin, H., & Nguyen, Q. V. H. (2022) · arXiv · doi:10.48550/arxiv.2209.02299 · Cited by 193
“) has 𝑟 = 𝐶 \ 𝐶 𝑓 .”
Metadata
- Authors
- Tarun, A. K., Chundawat, V. S., Mandal, M., & Kankanhalli, M.
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2024-09
- Volume
- 35
- Issue
- 9
- Pages
- 13046-13055
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W3213758632
- Cited by
- 182
- References
- 32
- FWCI
- 15.99
- Type
- journal article
- Language
- en
- Open access
- green
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.