The DOI matches its Crossref record; 37 of the 38 references it cites were found in a registry or an index.
FedEraser: Enabling Efficient Client-Level Data Removal from Federated Learning Models
Abstract
Federated learning (FL) has recently emerged as a promising distributed machine learning (ML) paradigm. Practical needs of the "right to be forgotten" and countering data poisoning attacks call for efficient techniques that can remove, or unlearn, specific training data from the trained FL model. Existing unlearning techniques in the context of ML, however, are no longer in effect for FL, mainly due to the inherent distinction in the way how FL and ML learn from data. Therefore, how to enable efficient data removal from FL models remains largely under-explored. In this paper, we take the first step to fill this gap by presenting FedEraser, the first federated unlearning method-ology that can eliminate the influence of a federated client’s data on the global FL model while significantly reducing the time used for constructing the unlearned FL model. The basic idea of FedEraser is to trade the central server’s storage for unlearned model’s construction time, where FedEraser reconstructs the unlearned model by leveraging the historical parameter updates of federated clients that have been retained at the central server during the training process of FL. A novel calibration method is further developed to calibrate the retained updates, which are further used to promptly construct the unlearned model, yielding a significant speed-up to the reconstruction of the unlearned model while maintaining the model efficacy. Experiments on four realistic datasets demonstrate the effectiveness of FedEraser, with an expected speed-up of 4× compared with retraining from the scratch. We envision our work as an early step in FL towards compliance with legal and ethical criteria in a fair and transparent manner.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Two evaluation parameters are specified: attack precision and attack recall , where attack precision denotes the proportion of unlearned samples that is expected to participate in the training process.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“In calibration training and update calibration steps, several rounds of a calibration retraining process are performed to approximate the unlearning updates without the target client.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“In addition, a prediction difference metric is also provided, which measures the difference in prediction probabilities between the original global model and the unlearned model.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“Second, this solution also requires caching of intermediate data, which will cost more storage.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“In the calibrated update aggregating and the unlearned model updating steps, standard federated learning aggregation operations are used to aggregate those unlearning updates and further update the global model.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“Liu et al. [54] present an experimental verification method based on a membership inference attack.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“Based on the idea of trading the central server's storage for the unlearned model's construction, Liu et al. [54] proposed an efficient federated unlearning methodology, FedEraser .”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“Historical parameter updates from the clients are stored in the central server during the training process, and then the unlearning process unfolds in four steps: (1) calibration training , (2) update calibrating , (3) calibrated update aggregating , and (4) unlearned model updating , to achieve the unlearning purpose.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“This eliminates the influence of the target data.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“However, the effectiveness of this scheme will decrease dramatically as the number of unlearning requests increases; this is because the gradients are cached during the training phase, and the unlearning process will not update these gradients to satisfy subsequent unlearning requests [54].”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“Attack recall denotes the fraction of unlearned samples that can be correctly inferred as part of the training dataset.”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“They are mostly designed to leverage the special characteristics of a particular learning process or training scheme [24, 47, 54].”
From Machine Unlearning: A Survey (2024) · cites this paper as [54]
In the citing paper
“The calibration process during the unlearned model training relies on the historical updates of the participating clients. The limited store capability of the hardware makes it hard to deploy in practice.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [224]
In the citing paper
“In [224], the federated unlearning methodology, namely, FedEraser, is proposed. In this scheme, the central server stores the historical updates received from clients during the global model training process. Once the global model converges, the FedEraser reconstructs an unlearned model in the central server based on the stored historical parameters.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [224]
In the citing paper
“In the FedEraser design, no substantial modification is required to the existing WFL architecture and the training process of the participants. Thus, the proposed method is easy to implement.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [224]
In the citing paper
“although the training data and the training process are not required, the FedEraser must target the attacker client, which is also pretty hard in actual implementation.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [224]
In the citing paper
“However, such defense methods [218], [224] require the historical information of local model updates and are not compatible with SecAgg, which brings more difficulty in the practical implementation.”
From Data and model poisoning backdoor attacks on wireless federated learning, and the defense mechanisms: A comprehensive survey (2024) · cites this paper as [224]
Citations
Cites
Communication-Efficient Learning of Deep Networks from Decentralized Data
McMahan, H. B., Moore, E., Ramage, D., Hampson, S., & Arcas, B. A. Y. (2016) · arXiv · doi:10.48550/arxiv.1602.05629 · Cited by 14,215
Deep Learning with Differential Privacy
Abadi, M., Chu, A., Goodfellow, I., McMahan, H. B., Mironov, I., Talwar, K., & Zhang, L. (2016) · Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2976749.2978318 · Cited by 6,578
Federated 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
Federated learning: Challenges, methods, and future directions
Li, T., Sahu, A. K., Talwalkar, A., & Smith, V. (2020) · IEEE Signal Processing Magazine · doi:10.1109/msp.2020.2975749 · Cited by 6,210
Dwork, C. (2006) · Lecture notes in computer science · doi:10.1007/11787006_1 · Cited by 6,125
Membership 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
Federated Learning: Strategies for Improving Communication Efficiency
Konečný, J., McMahan, H. B., Yu, F. X., Richtárik, P., Suresh, A. T., & Bacon, D. (2016) · arXiv · doi:10.48550/arxiv.1610.05492 · Cited by 3,766
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
Nasr, M., Shokri, R., & Houmansadr, A. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00065 · Cited by 1,760
Exploiting Unintended Feature Leakage in Collaborative Learning
Melis, L., Song, C., De Cristofaro, E., & Shmatikov, V. (2019) · 2019 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2019.00029 · Cited by 1,734
Research works printed but not linked: 2
- kone?n?, 2016, Federated learning: Strategies for improving communication efficiency, CoRR
- chen, 2016, Differ-entially private regression diagnostics, Proceedings of IEEE ICDM, 81
Cited by
Sorted by citations
Items 201–247 of 247
Federated Camouflaged Poisoning Attack in Federated Unlearning
Lai, W., Yan, Q., Liang, S., & Zhong, K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463455
FedSKU: Defending Backdoors in Federated Learning Through Selective Knowledge Unlearning
Xie, G., Zhou, Y., & Liu, B. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11463673
Top-1 Compression Suffices for Federated Unlearning with the Help of Adaptive Error Feedback
Xiao, B., Liu, S., & Ling, Q. H. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11462604
Federated Illusion: Multi-Level Geometric Privacy Audit for Federated Graph Unlearning
Han, H., Huang, Y., Xie, Z., & Pang, J. (2026) · Information · doi:10.3390/info17050424
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
Kundalwal, M. K., Mamta, Mishra, D., & Ekbal, A. (2026) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv61042.2026.00142
PrivEraserVerify: Efficient, Private, and Verifiable Federated Unlearning
Goswami, P., Islam, M. K., & Yeafi, A. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491311
HQSU: Hybrid Quantum Selective Unlearning for Backdoor Mitigation in Federated Learning
Don, A. K. K., Khalil, I., Edirimannage, S., Daluwatta, W., Elvitigala, C., & Ng, J. S. (2026) · International Conference on Quantum Communications, Networking, and Computing (QCNC) · doi:10.1109/qcnc69040.2026.00128
Dual asymmetric momentum improves federated class unlearning in edge systems
Patra, A., Mayaluri, Z. L., Sahoo, P. K., & Kumawat, G. (2026) · Scientific Reports · doi:10.1038/s41598-026-45631-w
Unlearning in Federated Learning Settings
Halimi, A., Kadhe, S., Rawat, A., & Baracaldo, N. (2026) · Synthesis lectures on computer vision · doi:10.1007/978-3-032-17282-2_16
Toward Trustworthy IIoT: A Reinforcement Learning Framework With Federated Unlearning
Annunziata, D., Qi, P., Li, K., & Piccialli, F. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3697565
DynamicFU: Contribution-Aware Dynamic Federated Unlearning for Industrial IoT
Wu, Z., He, B., Si, Z., Liao, X., & Su, C. (2026) · Sensors · doi:10.3390/s26123714
Federated Unlearning Activated Backdoor Attacks
Chen, J., Shi, W., Hu, C., Lu, J., Abdelmoniem, A. M., & Wang, C. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3703139
Self-citationFedGA-RVI: Efficient Federated Unlearning via Adaptive Recovery Optimization and Smart Stopping
Xing, S., Cai, J., Li, W., Zhang, N., & Wang, J. (2026) · International Seminar on Artificial Intelligence, Networking and Information Technology (AINIT) · doi:10.1109/ainit70033.2026.11557826
FedCleanse: A Post-Hoc Unlearning Technique for Federated Learning Against Label Flipping Attacks
Li, S., Zhan, P., & Feng, Y. (2026) · International Conference on Electronic Information Engineering, Big Data and Computer Technology (EIBDCT) · doi:10.1109/eibdct69742.2026.11567006
Secure Federated Unlearning for IoT-FL Systems
Zhao, W., Wang, T. C., Zhou, X., Jiang, W., & Wang, P. (2026) · International Symposium on Computer Technology and Information Science (ISCTIS) · doi:10.1109/isctis70043.2026.11572404
Jain, S., Bhattacharya, P., Chatterjee, S., Roy, S., Gadekallu, T. R., & Shetty, S. S. (2026) · International Wireless Communications and Mobile Computing Conference (IWCMC) · doi:10.1109/iwcmc69287.2026.11579903
Redundancy-Aware Federated Unlearning with Reverse and Selective Distillation
Zheng, J., Li, K., Zhou, C., Zhu, D., Pan, C., & Du, X. (2026) · International Conference on Machine Intelligence Theory and Applications (MiTA) · doi:10.1109/mita69365.2026.11582666
pMoEFU: Class-Level Federated Unlearning with Personalized Mixture of Experts
Wang, J., Lin, Y., Gao, Z., Du, H., Wang, J., & Fan, J. (2025) · IEEE Globecom Workshops (GC Wkshps) · doi:10.1109/gcwkshps68340.2025.11591111
Qian, Y., Ma, L., Yu, G., Zheng, M., Huang, M., Li, Q., & Wang, X. (2026) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2026.3712254
Graph Unlearning for MLaaS: Toward Flexible Privacy Adjustment via Influenced Subgraph
Li, Y., Zhao, Y., Tan, Q., Wang, Y.-G., Wang, L., Wei, T., Zhu, M., Xu, K., & Zhao, Y.-J. (2026) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2026.3715465
FU-TTA: Federated Unlearning for Test-Time Adaptation
Qi, P., & Tu, J. (2026) · International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) · doi:10.1109/mlise70044.2026.11607543
Machine unlearning through model forgetting techniques: application area and emerging methods
Büyüktanır, B., Kucur, E. N., Kuyumcu, Z., Ozdemir, N., Altınkaya, Ş., Baydoğmus, G. K., & Yıldız, K. (2026) · Cluster Computing · doi:10.1007/s10586-026-06300-9
Securing Smart Agriculture with Communication-Efficient Federated Unlearning
Pudasaini, U., Ding, Z., & Huang, J. (2026) · IEEE International Conference on High Performance Switching and Routing (HPSR) · doi:10.1109/hpsr68369.2026.11615191
DRFU: Federated Unlearning with Reverse KL-Divergence-based Knowledge Distillation
Nguyen, T. N., Tran, H. A., Nguyễn, H. H., Hoang, N.-T., Zhang, Y., Konda, M., & Tran, T. X. (2026) · IEEE Cloud Summit · doi:10.1109/cloudsummit68932.2026.00035
Network Digital Untwinning: Towards Backward Optimization of Digital Twins
Zhang, Z., Chen, D., Gao, A., Wang, M., Chen, M., Fang, M., Yang, X., & Liu, Y. (2026) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/2575-8411.2026.00128
Ding, Z., Wu, B., & Huang, J. (2026) · IEEE International Conference on Distributed Computing Systems (ICDCS) · doi:10.1109/2575-8411.2026.00143
Introduction of Machine Unlearning
Wang, W., & Yu, S. (2026) · Digital Privacy and Security · doi:10.1007/978-981-92-1142-5_1
Kim, H., Moon, J., & Baik, N. (2026) · Electronics · doi:10.3390/electronics15163643 · Cited by 1
Xu, J., & Jia, X. (2026) · Wireless networks · doi:10.1007/978-3-032-30978-5_1
Conclusion, Practical Challenges, and Future Directions
Xu, J., & Jia, X. (2026) · Wireless networks · doi:10.1007/978-3-032-30978-5_7
SiftFL: Scheduling-Based Robust Backdoor Detection in Federated Learning
Hashem, E., Felemban, M., Mahmood, S., & Barnawi, A. Y. (2026) · IEEE Access · doi:10.1109/access.2026.3727396
Zhang, S., Wang, X., Zeng, R., Huang, M., Gu, Y., & He, Q. (2026) · Computer Networks · doi:10.1016/j.comnet.2026.112708
Channel-Aware Federated Unlearning With Gradient Perturbation in Open Radio Access Networks
Shah, S. D. A., Nezami, Z., & Hoseini, S. A. (2026) · IEEE Wireless Communications Letters · doi:10.1109/lwc.2026.3730846
A Review on Machine Unlearning Algorithms and Privacy Protection
Aliprantis, J., & Kalloniatis, C. (2026) · Electronics · doi:10.3390/electronics15184057
Fluid antenna assisted federated unlearning system
Chen, Y., Yang, Z., Xu, H., Ceng, C., Chen, Y., Wong, K., & ZHANG, C. (2026) · Scientia Sinica Informationis · doi:10.1360/ssi-2026-0205
Structured distillation for few-shot heterogeneous federated unlearning
Zhang, J., Zhou, B., Wang, Z., Zhao, M., & Wang, P. (2026) · Knowledge-Based Systems · doi:10.1016/j.knosys.2026.117005
FedDRU: Depth-Aware Residual Client Unlearning for Heterogeneous Federated Learning
Leng, J., Zhong, Z., Xin, H., & An, K. (2026) · International Conference on Big Data and Information Analytics (BigDIA) · doi:10.1109/bigdia71496.2026.11684651
OIAFed: All-in-One Federated Learning Framework
Chen, T., Zhou, L., Zhang, B., Liu, Y., Guo, S., Meng, L., Luo, D., Sun, Y., & Zhang, W. (2026) · IEEE International Conference on Intelligence and Security Informatics (ISI) · doi:10.1109/isi69914.2026.11685850
Practical Federated Unlearning: A Target Client-Driven Approach to Model Forgetting
Tian, L., Lin, F., Qin, Z., Qi, J., Li, M., & Ren, K. (2026) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2026.3734781
Manipulating Feature Space for Generalizable Data Characterization in Federated Learning
Raouf, I., & Wang, P. E. (2026) · Manufacturing Letters · doi:10.1016/j.mfglet.2026.08.048
FedOrtho: Efficient Federated Unlearning via Orthogonal Convolution and Adaptive Soft Pruning
龚庆辉, Yang, X., Chen, X., Lai, J., Meng, H., & Tang, X. (2026) · doi:10.1109/cvprf71909.2026.00769
FedErase: Personalized Federated Unlearning for Text-to-Image Diffusion Models
Geng, T., Liang, W., Wang, S., She, R., & Tay, W. P. (2026) · doi:10.1109/cvprf71909.2026.00390
MMT: Achieving Exact Federated Unlearning with Improved Post-unlearning Performance
Zhang, Z., Bui, N., Verma, A., Ding, B., & Low, B. K. H. (2026) · Machine Learning · doi:10.1007/s10994-026-07117-8
Model-Space Reversal for Efficient Federated Agnostic Unlearning
Tang, X., Ying, Z., Pan, Z., Wang, Y., Liehuang, Z., Niyato, D., Zhou, W., & Ma, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-92-6831-3_9
Zhang, R., Chen, J., Chen, J., Bai, Y., Chen, X., & Guo, S. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11729738
Jain, S., Gupta, S., Bhattacharya, P., Roy, S., Shetty, S. S., Jhaveri, R. H., & Alrabaee, S. (2026) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn69854.2026.11728865
Metadata
- Authors
- Liu, G., Ma, X., Yang, Y., Wang, C., & Liu, J.
- Affiliations
- Huazhong University of Science and Technology (CN)
- Hubei University (CN)
- Simon Fraser University (CA)
- Venue
- 2021 IEEE/ACM 29th International Symposium on Quality of Service (IWQOS)
- Publisher
- IEEE
- Published
- 2021-06-25
- Pages
- 1-10
- ISSN
- 1548-615X (ISSN-L)
- OpenAlex
- W3197363474
- Cited by
- 248
- References
- 38
- Citations by year
- 2026: 66 · 2025: 94 · 2024: 62 · 2023: 23 · 2022: 3
- FWCI
- 10.08
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- International Workshop on Quality of Service (publishedVersion)
- Funders
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
- Natural Science Foundation of Hubei Province
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Physical Sciences › Computer Science › Computer Networks and Communications › Cryptography and Data Security
- Keywords
- federated learning, data deletion, right to be forgotten, data poisoning, model reconstruction
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
