REVIEW 7 cited by
Federated Unlearning: How to Efficiently Erase a Client in FL?
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
With privacy legislation empowering the users with the right to be forgotten, it has become essential to make a model amenable for forgetting some of its training data. However, existing unlearning methods in the machine learning context can not be directly applied in the context of distributed settings like federated learning due to the differences in learning protocol and the presence of multiple actors. In this paper, we tackle the problem of federated unlearning for the case of erasing a client by removing the influence of their entire local data from the trained global model. To erase a client, we propose to first perform local unlearning at the client to be erased, and then use the locally unlearned model as the initialization to run very few rounds of federated learning between the server and the remaining clients to obtain the unlearned global model. We empirically evaluate our unlearning method by employing multiple performance measures on three datasets, and demonstrate that our unlearning method achieves comparable performance as the gold standard unlearning method of federated retraining from scratch, while being significantly efficient. Unlike prior works, our unlearning method neither requires global access to the data used for training nor the history of the parameter updates to be stored by the server or any of the clients.
Forward citations
Cited by 7 Pith papers
-
pFedUL: Layer-Aware Federated Unlearning for Personalized Federated Learning
Layer-aware selective unlearning for personalized FL matches near-retrain forgetting while retaining ~97% personalized accuracy for remaining clients across four pFL architectures.
-
Lethe: Adapter-Augmented Dual-Stream Update for Persistent Knowledge Erasure in Federated Unlearning
A federated-unlearning method that keeps erased knowledge from coming back during continued training, reporting under 1% resurfacing in most tested settings.
-
BadFU: Backdoor Federated Learning through Adversarial Machine Unlearning
A malicious federated-learning client can hide a backdoor by adding trigger-labeled samples plus camouflage samples, then activate it by requesting unlearning of the camouflage samples.
-
DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems
DRAUN reconstructs unlearned client images from federated unlearning updates by simulating possible unlearning losses and matching gradients, exposing privacy leakage in optimization-based federated unlearning.
-
On the importance of multiple training seeds for evaluating machine unlearning
Machine-unlearning evaluation with a single training seed can misrepresent method performance, particularly for deterministic unlearning methods, and extra unlearning seeds do not fix it.
-
SecureT2I: No More Unauthorized Manipulation on AI Generated Images from Prompts
A diffusion editing model is fine-tuned with a blur target for forbidden images and the original output for permitted images, claiming selective suppression of unauthorized edits.
-
Realistic Image-to-Image Machine Unlearning via Decoupling and Knowledge Retention
The paper claims that gradient ascent on forget samples makes them out-of-distribution for an unlearned image-to-image model, with formal guarantees and a data-poisoning audit.
Discussion (0). Continue with ORCID to comment.