Machine Unlearning: A Survey
Open accessThe DOI matches its Crossref record; 132 of the 132 references it cites were found in a registry or an index; 140 of the 233 sources its claims cite were checked for support.
Abstract
This survey captures the key concepts of unlearning techniques and highlights outstanding issues with unlearning techniques, along with feasible directions for new research opportunities.
Overview
CoChat Summary
TL;DR
This survey reviews machine unlearning, proposing a taxonomy that divides existing techniques into data reorganization and model manipulation, with verification mechanisms reviewed alongside each category. It summarizes advantages, limitations, and open issues, including universality, security, verification, and applications.
Key findings
- The paper proposes a taxonomy of unlearning methods: data reorganization (data obfuscation, data pruning, data replacement) and model manipulation (model shifting, model pruning, model replacement). Verification methods are categorized as empirical (retraining-based, attack-based, relearn time-based, accuracy-based) or theoretical (theory-based, information bound-based).
- Data reorganization schemes often retain intermediate parameters and use the original training dataset; they can support complex models and strong unlearning but may affect consistency and accuracy and require additional storage. Data obfuscation seldom completely unlearns information; data pruning can reduce accuracy as sub-models train on partial data; data replacement struggles to retain all original dataset information.
- Model manipulation schemes directly adjust model parameters, reducing intermediate storage, but most focus on simple models or special assumptions; removing information from standard deep networks remains an open problem. They may affect consistency or prediction accuracy, and theory-based or information-bound verification is more convincing but complex and limited to specified models.
- Open questions include universality of unlearning solutions, security risks where unlearning can increase privacy leakage, user-friendly verification, and broader applications. Future directions include information synchronization, federated unlearning, disturbance techniques, feature-based unlearning, and game-theory-based balance.
Methods
- Design: a comprehensive survey that proposes a novel taxonomy based on unlearning rationale and strategy, summarizes state-of-the-art methods, reviews verification methods, and discusses open issues and future directions.
- Data or sample: existing machine unlearning literature; the paper does not state a systematic search protocol, inclusion criteria, or quantitative synthesis.
- Analysis: qualitative classification and comparison across dimensions such as whether original training data is required, whether intermediate data is cached, supported classes and models, unlearning targets, and verification methods.
Limitations
- The paper states limitations of existing unlearning schemes: exact unlearning can only be achieved for simple and well-structured models; many schemes lack theoretical verification; data reorganization can incur storage and accuracy costs; model manipulation is often limited to simple models or special assumptions; and many verification methods are one-sided or not user-friendly.
- The paper does not explicitly state limitations of the survey itself. Evident from the text: it does not report a systematic review protocol or quantitative meta-analysis, and its coverage reflects the literature cited up to the publication date.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
104 Valid · 10 Not valid · 55 Not checked · 91 Own results and interpretations
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“However, since the summation form comes from statistical query (SQ) learning, and only a few machine learning algorithms can be implemented as SQ learning, such as naïve bayes classifiers [83], support vector machines [84], and k-means clustering [85], this scheme has low applicability.”
What the sources say
- Disputedcites [29] [29] Yinzhi Cao and Junfeng Yang. 2015. Towards making systems forget with machine unlearning. In IEEE Symposium on Security and Privacy . IEEE Computer Society, 463-480. DOI: http://dx.doi.org/10.1109/SP.2015.35 - sourceExperimental — accuracy not yet measured
The Machine Unlearning section says many algorithms—including naïve Bayes classifiers, support vector machines, and k-means clustering—can be implemented as SQ learning and describes the approach as general. The Adaptive SQ Learning section says very few practical learning algorithms cannot be converted to its adaptive SQ form. These passages contradict the claim that only a few can be implemented and that this makes the scheme minimally applicable. (LLM, conf=0.92)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“However, this solution will result in a significant reduction in accuracy when dealing with complex models.”
What the sources say
- Disputedcites [93] [93] Yi Liu, Lei Xu, Xingliang Yuan, Cong Wang, and Bo Li. 2022. The right to be forgotten in federated learning: An efficient realization with rapid retraining. In IEEE Conference on Computer Communications . IEEE, 1749-1758. DOI: http://dx.doi.org/10.1109/INFOCOM48880.2022.9796721 - sourceExperimental — accuracy not yet measured
The Evaluation (p. 9) reports that Liu et al.’s algorithm achieves accuracy comparable to retraining from scratch and says momentum compensates for the model-utility loss from its approximation. The Introduction (p. 2) describes the solution as model agnostic and reports only a small accuracy loss on CelebA, contrary to the claimed significant reduction for complex models. (LLM, conf=0.87)
Checked by a reasoning model — may be wrong.
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
At least one cited source doesn’t support this claim or points to a different paper, and none confirmed it — see the verdicts below.
In the paper
“The other studies [49, 50] did not provide a method for verifying the unlearning process.”
What the sources say
- Disputedcites [49] [49] [Varun Gupta, Christopher Jung, Seth Neel, Aaron Roth, Saeed Sharifi-Malvajerdi, and Chris Waites. 2021. Adaptive machine unlearning. In Advances in Neural Information Processing Systems: Annual Conference on Neural Information Processing Systems . 16319-16330. Retrieved from https://proceedings.neurips.cc/paper/2021/hash/ 87f7ee4fdb57bdfd52179947211b7ebb-Abstract.html.](https://proceedings.neurips.cc/paper/2021/hash/87f7ee4fdb57bdfd52179947211b7ebb-Abstract.html) - sourceExperimental — accuracy not yet measured
Section C.2 (pp. 21–22) describes a method for testing an unlearning guarantee: compare outcomes after deletion with outcomes after full retraining and use confidence intervals to assess the difference. The paper uses that method to reject a perfect-unlearning guarantee for the tested SISA algorithms. This contradicts the unqualified claim that it provides no method for verifying unlearning, although the test is not a certificate for an individual deletion request. (LLM, conf=0.86)
Checked by a reasoning model — may be wrong.
- Could not verifycites [50] [50] Seth Neel, Aaron Roth, and Saeed Sharifi-Malvajerdi. 2021. Descent-to-delete: Gradient-based methods for machine unlearning. In Algorithmic Learning Theory (Proceedings of Machine Learning Research , Vol. 132). PMLR, 931-962. Retrieved from http://proceedings.mlr.press/v132/neel21a.html. - sourceExperimental — accuracy not yet measured
The paper defines an indistinguishability-based unlearning guarantee (Model and Preliminaries, pp. 6–7) and proves that its algorithms satisfy it (Theorem 3.2, p. 11). Those passages do not establish whether it provides a method for verifying that an unlearning process was carried out; a search for verification and auditing found no passage that settles that point. (LLM, conf=0.69)
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
Some cited sources support this claim and some don’t — read each source’s verdict below.
In the paper
“The unlearning schemes proposed in References [29, 30, 33, 47, 68, 69] are essentially based on a retraining mechanism that naturally has a verifiability property.”
What the sources say
- Disputedcites [29] [29] Yinzhi Cao and Junfeng Yang. 2015. Towards making systems forget with machine unlearning. In IEEE Symposium on Security and Privacy . IEEE Computer Society, 463-480. DOI: http://dx.doi.org/10.1109/SP.2015.35 - sourceExperimental — accuracy not yet measured
The “B. Machine Unlearning” section explicitly describes the proposed approach as unlearning “without retraining from scratch”: it subtracts the forgotten data from stored summations and updates the model. The “C. Empirical Results” section compares unlearning with retraining to evaluate completeness, but that does not make retraining the mechanism on which the scheme is based. No page numbers are available in our copy. (LLM, conf=0.88)
Checked by a reasoning model — may be wrong.
- Not checked — no full text of the sourcecites [30] [30] Lucas Bourtoule, Varun Chandrasekaran, Christopher A. Choquette-Choo, Hengrui Jia, Adelin Travers, Baiwu Zhang, David Lie, and Nicolas Papernot. 2021. Machine unlearning. In 42nd IEEE Symposium on Security and Privacy . IEEE, 141-159. DOI: http://dx.doi.org/10.1109/SP40001.2021.00019 - source
- Partly supportedcites [33] [33] Chong Chen, Fei Sun, Min Zhang, and Bolin Ding. 2022. Recommendation unlearning. In ACMWebConference . ACM, 2768-2777. DOI: http://dx.doi.org/10.1145/3485447.3511997 - sourceExperimental — accuracy not yet measured
Section 4.1 (page unavailable) says RecEraser unlearns data by retraining the affected submodel and aggregation component. The discussion of exact unlearning says its aim is complete removal of the requested data, but our copy does not say that this retraining mechanism naturally has a verifiability property. (LLM, conf=0.83)
- Partly supportedcites [47] [47] [Min Chen, Zhikun Zhang, Tianhao Wang, Michael Backes, Mathias Humbert, and Yang Zhang. 2022. Graph unlearning. In ACM SIGSAC Conference on Computer and Communications Security . ACM, 499-513. DOI: http://dx.doi.org/ 10.1145/3548606.3559352](http://dx.doi.org/10.1145/3548606.3559352) - sourceExperimental — accuracy not yet measured
Section 2.2 (pp. 2–3) describes retraining as an unlearning method, and says GraphEraser removes a requested node and retrains its shard model. The cited paper does not establish the claimed verifiability property; its description of retraining as easy to enforce is not a statement that the result can be verified. (LLM, conf=0.83)
- Not checked — no full text of the sourcecites [68] [68] Wei Qian, Chenxu Zhao, Huajie Shao, Minghan Chen, Fei Wang, and Mengdi Huai. 2022. Patient similarity learning with selective forgetting. In IEEE International Conference on Bioinformatics and Biomedicine . IEEE, 529-534. DOI: http://dx.doi.org/10.1109/BIBM55620.2022.9995016 - source
- Partly supportedcites [69] [69] Haonan Yan, Xiaoguang Li, Ziyao Guo, Hui Li, Fenghua Li, and Xiaodong Lin. 2022. ARCANE: An efficient architecture for exact machine unlearning. In 31st International Joint Conference on Artificial Intelligence . ijcai.org, 4006-4013. DOI: http://dx.doi.org/10.24963/ijcai.2022/556 - sourceExperimental — accuracy not yet measured
Section 1.2 describes exact unlearning as removing data and retraining, and calls that approach naturally reliable. The Discussion also says exact unlearning is based on retraining at the algorithmic level. Neither passage establishes the distinct claim that these schemes naturally have a verifiability property. (LLM, conf=0.83)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Disputed
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Significantly, model manipulation methods usually give a verifiability guarantee using theory-based and information bound-based methods [40, 41, 43].”
What the sources say
- Partly supportedcites [40] [40] Aditya Golatkar, Alessandro Achille, and Stefano Soatto. 2020. Eternal sunshine of the spotless net: Selective forgetting in deep networks. In IEEE/CVF Conference on Computer Vision and Pattern Recognition . Computer Vision Foundation/IEEE, 9301-9309. DOI: http://dx.doi.org/10.1109/CVPR42600.2020.00932 - sourceExperimental — accuracy not yet measured
Section 2 derives a KL-divergence bound that guarantees robustness to any readout function, and Section 5.2 says the authors’ proposed methods provide an upper bound on remaining information. The paper supports a theory- and information-bound-based guarantee for its own forgetting methods, but does not establish that model manipulation methods usually provide such guarantees. (LLM, conf=0.84)
- Partly supportedcites [41] [41] Chuan Guo, Tom Goldstein, Awni Y. Hannun, and Laurens van der Maaten. 2020. Certified data removal from machine learning models. In 37th International Conference on Machine Learning (Proceedings of Machine Learning Research , Vol. 119). PMLR, 3832-3842. Retrieved from http://proceedings.mlr.press/v119/guo20c.html. - sourceExperimental — accuracy not yet measured
The Introduction (p. 1) describes a theoretical guarantee for the paper’s certified-removal mechanism, and Section 3.1 (p. 3) derives it using bounds on the gradient residual and max-divergence. The paper does not establish that model-manipulation methods *usually* provide such guarantees, nor does it characterize them generally as verifiability guarantees. (LLM, conf=0.85)
- Not checked — no full text of the sourcecites [43] [43] Aditya Golatkar, Alessandro Achille, and Stefano Soatto. 2020. Forgetting outside the box: Scrubbing deep networks of information accessible from input-output observations. In 16th European Conference on Computer Vision (Lecture Notes in Computer Science , Vol. 12374). Springer, 383-398. DOI: http://dx.doi.org/10.1007/978-3-030-58526-6\_23 - source
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Partly supported
86 more claims · 36 with their cited sources checked
Create a free account to see all 260 claims and to verify the 12 references still open.
- Probably not a substantial claim. 128
- It may state two separate claims as one. 68
- The quote only partly states this claim. 1
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.1 Unlearning Taxonomy · p. 10
“| Model Pruning [54-56] | Replaces partial parameters with pre-calculated parameters”
§ 3.1 Unlearning Taxonomy · p. 9
“Model pruning: In model pruning, the model provider prunes some parameters from the trained models to unlearn the given samples”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.1 Unlearning Taxonomy · p. 9
“D i , 0 < i < m are the sub-datasets”
§ 3.1 Unlearning Taxonomy · p. 9
“D → D 1 ∪ D 2 ∪ · · · ∪ D m”
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 3.1 Unlearning Taxonomy · p. 10
“| Model Replacement [57-60] | Prunes some parameters from already-trained models”
§ 3.1 Unlearning Taxonomy · p. 9
“Model replacement: In model replacement, the model provider directly replaces some parameters with pre-calculated parameters”
Citations
Cites
A Comprehensive Survey on Graph Neural Networks
Wu, Z., Pan, S., Chen, F., Long, G., Zhang, C., & Yu, P. S. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2020.2978386 · Cited by 11,000 · cited 1×
“To analyze the rich information in these graphs, graph neural networks (GNNs) have shown unprecedented advantages [74, 75].”
BackgroundSelf-citationMachine learning: Trends, perspectives, and prospects
Jordan, M. I., & Mitchell, T. M. (2015) · Science · doi:10.1126/science.aaa8415 · Cited by 9,955 · cited 1×
“In recent years, machine learning has seen remarkable progress and wide exploration across every field of artificial intelligence (AI) [1].”
BackgroundFederated Machine Learning: Concept and Applications
Yang, Q., Liu, Y., Chen, T., & Tong, Y. (2019) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3298981 · Cited by 6,322
Mosaic organization of DNA nucleotides
Peng, C.-K., Buldyrev, S. V., Havlin, S., Simons, M., Stanley, H. E., & Goldberger, A. L. (1994) · Physical Review E · doi:10.1103/physreve.49.1685 · Cited by 4,985 · cited 1×
“They irst introduce a process called detrended luctuation analysis [81], which quantiies the inluence of the unlearned data on the model parameters, termed temporal residual memory.”
BackgroundMembership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754
Model Inversion Attacks that Exploit Confidence Information and Basic Countermeasures
Fredrikson, M., Jha, S., & Ristenpart, T. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813677 · Cited by 2,961 · cited 2×
“This is because membership inference attacks [5] and model inversion attacks [6] can reveal information about the speciic contents of a training dataset.”
BackgroundMethodFederated Learning in Mobile Edge Networks: A Comprehensive Survey
Lim, W. Y. B., Luong, N. C., Hoang, D. T., Jiao, Y., Liang, Y.-C., Yang, Q., Niyato, D., & Miao, C. (2020) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2020.2986024 · Cited by 2,565
Adaptive Federated Learning in Resource Constrained Edge Computing Systems
Wang, S., Tuor, T., Salonidis, T., Leung, K. K., Makaya, C., He, T., & Chan, K. (2019) · IEEE Journal on Selected Areas in Communications · doi:10.1109/jsac.2019.2904348 · Cited by 2,232
Understanding Black-box Predictions via Influence Functions
Koh, P. W., & Liang, P. (2017) · arXiv · doi:10.48550/arxiv.1703.04730 · Cited by 1,514 · cited 4×
“The model manipulation methods calculate the influence of each sample and offset that influence using a range of techniques [38], while data reorganization schemes usually reorganize the training dataset to simplify the unlearning process.”
BackgroundMethodInfluentialThe 26th USENIX Security Symposium 2017
Αλεξόπουλος, Ν., Kiayias, A., Zacharias, T., & Talviste, R. (2017) · USENIX Security Symposium · Cited by 1,168
Research works printed but not linked: 5
- Sebastian Schelter. 2020. “Amnesia’—Towards machine learning models that can forget user data very fast. In 10th Conference on Innovative Data Systems Research. Retrieved from http://cidrdb.org/cidr2020/papers/p32-schelter-cidr20.pdf.
- Pei-Hung Chen, Wei Wei, Cho-Jui Hsieh, and Bo Dai. 2021. Overcoming catastrophic forgetting by Bayesian generative regularization. In 38th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 139). PMLR, 1760–1770. Retrieved from http://proceedings.mlr.press/v139/chen21v.html.
- Zachary Izzo, Mary Anne Smart, Kamalika Chaudhuri, and James Zou. 2021. Approximate data deletion from machine learning models. In 24th International Conference on Artificial Intelligence and Statistics(Proceedings of Machine Learning Research, Vol. 130). PMLR, 2008–2016. Retrieved from http://proceedings.mlr.press/v130/izzo21a.html.
- Yinjun Wu, Edgar Dobriban, and Susan B. Davidson. 2020. DeltaGrad: Rapid retraining of machine learning models. In 37th International Conference on Machine Learning(Proceedings of Machine Learning Research, Vol. 119). PMLR, 10355–10366. Retrieved from http://proceedings.mlr.press/v119/wu20b.html.
- 10.5555/1953048.2021036 · doi:10.5555/1953048.2021036
Cited by
Items 101–157 of 157
Efficient Machine Unlearning by Model Splitting and Core Sample Selection
Egger, M., Bitar, R., & Urbanke, R. L. (2025) · IEEE Information Theory Workshop (ITW) · doi:10.1109/itw62417.2025.11240389 · Cited by 2
“We adopt the probabilistic framework as in [11], [14], [15], and formally state this generalized notion of exact unlearning.”
Can Federated Models Be Rectified Through Learning Negative Gradients?
Tahir, A., Tan, Z., & Babaagba, K. O. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-52265-9_2
Machine unlearning using a Multi-GaN based model
Hatua, A., Nguyen, T. V., & Sung, A. H. (2024) · AIP conference proceedings · doi:10.1063/5.0234688 · Cited by 1
OPMUS: A Win-Win Pricing Strategy for Machine Unlearning Service
Tang, M., Wang, W., & Yu, S. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0811-9_27
A Scheme of Dynamic Location Privacy-Preserving with Blockchain in Intelligent Transportation System
Zuo, X., Wang, M., Ye, D., et al. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-1525-4_2
An Efficient Federated Meta Unlearning Algorithm with Enhanced Privacy Protection
Wang, Y., Ying, Z., Pan, Z., Zhu, E., & Zhou, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-2864-3_9 · Cited by 1
Self-citationSong, Q., Wang, R., Li, Y., Yan, Y., Zhu, X., & Li, H. (2025) · Journal of Information and Intelligence · doi:10.1016/j.jiixd.2024.11.001
Robust Unlearning for Large Language Models
Gu, K., Rashid, M. R. U., Sultana, N., & Mehnaz, S. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-8186-0_12
Rethinking Privacy Protection for Recommender System in a Collaborative Way
Zhang, Y., Li, S., Lin, M., Shen, J., Yu, S., & Lin, J. (2025) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd64889.2025.11033239
Unlearning in Decision Tree Classifiers and Microcontroller Implementations
Karn, R. R., Roy, P. B., Knechtel, J., & Sinanoglu, O. (2025) · IEEE Conference on Artificial Intelligence (CAI) · doi:10.1109/cai64502.2025.00114
“It involves the deliberate removal or forgetting of information associated with a specific class or subset of data [5], [6].”
InfluentialAI-Associate: A Lightweight Architecture for Conversational Agents
Gani, U. A. S., Madankar, A., Shinde, A., Sonwane, A., & Durbade, S. (2025) · OPJU International Technology Conference on Smart Computing for Innovation and Advancement in Industry (OTCON) · doi:10.1109/otcon65728.2025.11070569
Huang, J., Deng, Y., Zhou, Y. X., Yang, Q., & Min, G. (2025) · IEEE Transactions on Fuzzy Systems · doi:10.1109/tfuzz.2025.3586297
Graph Unlearning System with Subgraph De-Isolation Measures
Li, Y., Cheng, D., Zhang, G., Li, C., & Zhang, S. (2025) · ACM Transactions on Autonomous and Adaptive Systems · doi:10.1145/3750734 · Cited by 2
Cer-FeaUn: Certified Feature Unlearning in Vertical Federated Learning
Wang, Y., Lu, Z., Liu, Z., Li, T., Chen, Z., & Susilo, W. (2025) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2025.3594851 · Cited by 6
Unlearning with Partial Label Learning
Bach, J., Grohsjean, A., Schwanenberger, C., & Stelldinger, P. (2025) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3733155.3733201 · Cited by 1
Machine Learning for Industrial Iot Cybersecurity: A Systematic ReviewPreprint
Dohin, A., Zkik, K., Akilal, A., Omar, M., & Akli, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5388573 · Cited by 2
Federated meta unlearning based on model decomposition and weighted aggregation
Wang, Y., Fan, Q., Pan, Z., Ying, Z., Zhang, Z., & Zhu, L. (2025) · Scientia Sinica Informationis · doi:10.1360/ssi-2025-0221 · Cited by 1
FedUP: Federated Unlearning With Prototypes
Huang, Y., Li, X., Chen, S., & Chen, S. (2025) · IEEE Transactions on Sustainable Computing · doi:10.1109/tsusc.2025.3612138 · Cited by 2
Hossain, P. S., Marasco, E., Lin, J., & King, M. C. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-06096-9_16
Boundary-Anchored Functional Duplication Attacks on Machine Unlearning
Shangguan, C., Li, Y., Wang, Y., & Song, Q. (2025) · IEEE International Conference on Privacy Computing and Data Security (PCDS) · doi:10.1109/pcds65695.2025.00035
The forget-set identification problem
D’Angelo, A., Gullo, F., & Stilo, G. (2025) · Machine Learning · doi:10.1007/s10994-025-06897-9
“In principle, this can be done by a complete retraining of the original model on the training set resulting from the removal of the unwanted training samples (Xu et al., 2024 ).”
InfluentialGao, K., Zhu, T., Ye, D., Liu, B., & Zhou, W. (2025) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2025.3630811 · Cited by 3
Self-citationXing, M., Zhou, J., Meng, S., Liu, N., & Zhang, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227397
“Approximate unlearning ensures that the distribution of the unlearned model is indistinguishable from that of the retrained model [17].”
LaVA: Flexible Machine Unlearning through Learnable Vector ArithmeticPreprint
Yang, X., Xu, Y., Zhang, X.-Y., Liang, J., & Tan, T. N. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5553904
A Survey on Continuous Unlearning in Generative AI: Approaches and Tradeoffs
Zhao, Y., Du, H., Lin, Y., Xiang, K., Niyato, D., & Poor, H. V. (2025) · IEEE Intelligent Systems · doi:10.1109/mis.2025.3616192 · Cited by 2
Colonna, L., & Oechtering, T. J. (2025) · Springer eBooks · doi:10.1007/978-3-031-97389-5_6 · Cited by 1
Improving Unlearning with Model Updates Probably Aligned with Gradients
Dine, V., Furon, T., & Faure, C. (2025) · ACM Workshop on Artificial Intelligence and Security (AISec) · doi:10.1145/3733799.3762975 · Cited by 1
Jonathan, M. K., & Gambetta, W. (2025) · International Conference on Advanced Informatics: Concepts, Theory and Applications (ICAICTA) · doi:10.1109/icaicta67604.2025.11335106
“However, this reliance on large datasets raises significant privacy and bias concerns, necessitating methods to selectively remove data from trained models [3].”
Privacy-Preserving Model Transcription With Differentially Private Synthetic Distillation
Liu, B., Ge, S., Wang, P., Li, S., & Liu, T. (2026) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2026.3659110
Safety in Graph Machine Learning: Threats and Safeguards
Wang, S., Dong, Y., Zhang, B., Chen, Z., Fu, X., He, Y., Shen, C., Zha, C., Chawla, N. V., & Li, J. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3660054 · Cited by 16
SUGPT: Efficient Graph Unsummarization for the Right to Be Forgotten
Li, Z. J., Ye, Q., Hu, H., Huang, X. S., Liu, J., & Meng, X. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3667723
Layer-Wise Unlearning for Model Adaption in Non-Stationary Environments
Zhou, Y., Wen, Y., Liu, Z., Liu, X., Yu, H., & Zhai, Y. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00186
“Machine unlearning algorithms can generally be categorized into data reorganization methods and model manipulation methods [18].”
Auditing Approximate Machine Unlearning for Differentially Private Models
Gu, Y., He, J., & Chen, K. (2025) · Proceedings · doi:10.1109/icdm65498.2025.00134
Quantum-Inspired Audio Unlearning: Towards Privacy-Preserving Voice Biometrics
Pathak, S., Shreshtha, S., Singh, R., & Vatsa, M. (2025) · IEEE International Joint Conference on Biometrics (IJCB) · doi:10.1109/ijcb65343.2025.11411246 · Cited by 4
Liu, N., Duan, J., Zhang, L., Liu, X., Ren, W., Zhu, T., & Min, G. (2026) · Neurocomputing · doi:10.1016/j.neucom.2026.133388
Self-citationMulti-Agent Machine Unlearning in Healthcare AI: Neural, Symbolic, and Coordination
Basith, F., Deepti, A. R., B, G. R., Meenakshi, H., R, N. H., & Deekshitha, K. (2025) · International Conference on Transformative Computing Technologies (ICTCT) · doi:10.1109/ictct69201.2025.00036
MOEA-SISA: Multiobjective Optimization to Improve Model Performance During Forgetting Data
Cao, B., Wang, Z., Chang, D., Liu, X., & Li, Y. (2026) · Chinese Journal of Electronics · doi:10.23919/cje.2024.00.052
FG-OrIU: Towards Better Forgetting via Feature-Gradient Orthogonality for Incremental Unlearning
Feng, Q., Tu, J., Kang, M., Zhao, H., Zhang, C., & Qian, H. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00190 · Cited by 10
Approach for Class-Wise Unlearning of Data Along with Learning of New Data
Guru, D. S., & Shivaprasad, D. L. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-18974-5_14
Membership Inference Attacks for Retrieval Based In-Context Learning for Document Question Answering
Kulkarni, T., Koskela, A., & Zumot, L. (2026) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml68715.2026.00062
“Beyond assessing privacy leakage, MIAs are also used as an heuristic metric to evaluate success of machine unlearning [36] methods.”
SGCN: A Robust Subsampling-Based GCN for Large-Scale Network with Out-of-Distribution Nodes
Zhu, Y., Li, J. J., Qin, L., et al. (2026) · Annals of Operations Research · doi:10.1007/s10479-026-07269-9
Towards refined unlearning: Utilizing the retain knowledge subspace and noise reduction
Kim, E., Choi, Y. J., & Cho, Y.-S. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.116284 · Cited by 1
Machine Unlearning in Smart Grids: A Cautionary Tale of Infrastructure Vulnerability
Paphitis, G., Marnerides, A. K., & Panteli, M. (2026) · IEEE Systems Man and Cybernetics Letters · doi:10.1109/lsmc.2026.3701875
Revisiting the machine unlearning ecosystem in vision: From afterthought to a lifecycle perspective
Marasco, E., Hicks, M., Slowik, B., Bourlai, T., & Ross, A. (2026) · Image and Vision Computing · doi:10.1016/j.imavis.2026.106059
Towards Selective Machine Unlearning via Specific Synaptic Dampening over Data Description
Pan, Z., Ping, Y., Wang, X., Yang, Q., Guo, C., & Lai, Y. (2026) · Annals of Data Science · doi:10.1007/s40745-026-00691-7
MU4Sum: Aspect Unlearning in LLM-based Document Summarization
Gallipoli, G., & Cagliero, L. (2026) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3828668
Certified Removal-Based Machine Unlearning for Data Poisoning in Cybermanufacturing
Tang, X., & Tian, W. (2026) · Journal of Manufacturing Science and Engineering · doi:10.1115/1.4072314
Alleviating Budgetary Challenges in Machine Unlearning Services Through Insurance
Tang, M., Wang, W., & Yu, S. (2026) · International Conference on Communications · doi:10.1109/icc59461.2026.11587356
“Regarding exact unlearning, it was costly initially, but a lot of work is dedicated to contribute the unlearning method with lower costs [16], although such a method may suffer from degradation in model utility and incomplete removals [16].”
Forgetting Similar Samples: Can Machine Unlearning Do it Better?
Xu, H., Zhu, T., Ye, D., Zhang, L., Wang, L., & Zhou, W. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3714774
Self-citationDA 2 -Unlearn: Dual-Adaptive Forget-Repair-Based Recommendation Unlearning
Dou, H., Lian, T., Song, X., & Ren, P. (2026) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3770855.3818203
Adaptive Machine Unlearning for Privacy PreservationPreprint
Markus, C., Sayeed, M. S., Mustapha, M., & Bukar, U. A. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7353462
Lee, J., Yoon, C., & Kim, H. (2026) · Advanced Engineering Informatics · doi:10.1016/j.aei.2026.105199
Nabith, M. A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-31233-4_17
Diffusion-Augmented Identity Unlearning for Visual Forensic Systems
Srilakshmi, V., Usha, A., Kiran, G. U., Reddy, B. V., Sai, K. K., & Reddy, K. S. (2026) · International Conference on Electronics and Sustainable Communication Systems (ICESC) · doi:10.1109/icesc70182.2026.11686900
Oblivious Exact (Un)Learning of Extremely Randomized Trees
Azogagh, S., Birba, Z. A., Gambs, S., & Killijian, M. (2026) · IEEE Conference on Secure and Trustworthy Machine Learning (SaTML) · doi:10.1109/satml68715.2026.00036
“In ensembles such as Random Forests or ERTs, predictions from multiple trees are aggregated—typically by majority vote for classification, or averaging for regression. c) Unlearning : Machine unlearning aims to remove the influence of a specific training sample, effectively “forgetting” it [53].”
SURGE: Structural Perturbation Response Field Guided Residual Distillation for Graph Unlearning
Shen, C., Wang, M., & Zhang, J. (2026) · Machine Learning · doi:10.1007/s10994-026-07176-x
Systemic privacy risks of personal data exposure through conversational large language model agents
Yahia, A. B., Kadir, I., Harrak, E. F. E., Chisembe, S., Abdallaoui, A., Hmaidi, A. E., & Dehbi, A. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02431-5
“Technically erasing parameter information from the model is difficult [10]; backup and logs of data are maintained for long periods of time [118]; editing information can be incorporated into the model for misuse [33] and the right to erasure is almost impossible to enforce [91].”
Influential
Metadata
- Authors
- Xu, H., Zhu, T., Zhang, L., Zhou, W., & Yu, P. S.
- Affiliations
- University of Technology Sydney (AU)
- City University of Macau (MO)
- University of Illinois Chicago (US)
- Venue
- ACM Computing Surveys
- Published
- 2023-08-28
- Volume
- 56
- Issue
- 1
- Pages
- 1-36
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W4379652910
- Semantic Scholar
- 0813793c140adf6f55b5fcb95ddfb12b8a924121
- Cited by
- 164
- References
- 122
- Citations by year
- 2026: 35 · 2025: 77 · 2024: 46 · 2023: 6
- FWCI
- 14.51
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Locations
- ACM Computing Surveys (publishedVersion, other-oa)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Funders
- Australian Research Council Discovery (DP200100946 and DP230100246)
- NSF (III-1763325, III-1909323, III-2106758, and SaTC-1930941)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Keywords
- machine unlearning, right to be forgotten, privacy, model retraining, privacy-preserving machine learning
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-12, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-12 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol).
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.