Federated Unlearning with Knowledge Distillation

• URL: http://arxiv.org/abs/2201.09441v1
• Date: Mon, 24 Jan 2022 03:56:20 GMT
• Title: Federated Unlearning with Knowledge Distillation
• Authors: Chen Wu and Sencun Zhu and Prasenjit Mitra
• Abstract summary: Federated Learning (FL) is designed to protect the data privacy of each client during the training process. With the recent legislation on right to be forgotten, it is crucially essential for the FL model to possess the ability to forget what it has learned from each client. We propose a novel federated unlearning method to eliminate a client's contribution by subtracting the accumulated historical updates from the model.
• Score: 9.666514931140707
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Federated Learning (FL) is designed to protect the data privacy of each client during the training process by transmitting only models instead of the original data. However, the trained model may memorize certain information about the training data. With the recent legislation on right to be forgotten, it is crucially essential for the FL model to possess the ability to forget what it has learned from each client. We propose a novel federated unlearning method to eliminate a client's contribution by subtracting the accumulated historical updates from the model and leveraging the knowledge distillation method to restore the model's performance without using any data from the clients. This method does not have any restrictions on the type of neural networks and does not rely on clients' participation, so it is practical and efficient in the FL system. We further introduce backdoor attacks in the training process to help evaluate the unlearning effect. Experiments on three canonical datasets demonstrate the effectiveness and efficiency of our method.

Related papers

• ConDa: Fast Federated Unlearning with Contribution Dampening [46.074452659791575]
  ConDa is a framework that performs efficient unlearning by tracking down the parameters which affect the global model for each client. We perform experiments on multiple datasets and demonstrate that ConDa is effective to forget a client's data.
  arXiv  Detail & Related papers  (2024-10-05T12:45:35Z)
• Fast-FedUL: A Training-Free Federated Unlearning with Provable Skew Resilience [26.647028483763137]
  We introduce Fast-FedUL, a tailored unlearning method for Federated Learning (FL) We develop an algorithm to systematically remove the impact of the target client from the trained model. Experimental results indicate that Fast-FedUL effectively removes almost all traces of the target client, while retaining the knowledge of untargeted clients.
  arXiv  Detail & Related papers  (2024-05-28T10:51:38Z)
• Blockchain-enabled Trustworthy Federated Unlearning [50.01101423318312]
  Federated unlearning is a promising paradigm for protecting the data ownership of distributed clients. Existing works require central servers to retain the historical model parameters from distributed clients. This paper proposes a new blockchain-enabled trustworthy federated unlearning framework.
  arXiv  Detail & Related papers  (2024-01-29T07:04:48Z)
• Federated Unlearning for Human Activity Recognition [11.287645073129108]
  We propose a lightweight machine unlearning method for refining the FL HAR model by selectively removing a portion of a client's training data. Our method achieves unlearning accuracy comparable to textitretraining methods, resulting in speedups ranging from hundreds to thousands.
  arXiv  Detail & Related papers  (2024-01-17T15:51:36Z)
• TOFU: A Task of Fictitious Unlearning for LLMs [99.92305790945507]
  Large language models trained on massive corpora of data from the web can reproduce sensitive or private data raising both legal and ethical concerns. Unlearning, or tuning models to forget information present in their training data, provides us with a way to protect private data after training. We present TOFU, a benchmark aimed at helping deepen our understanding of unlearning.
  arXiv  Detail & Related papers  (2024-01-11T18:57:12Z)
• Learn to Unlearn for Deep Neural Networks: Minimizing Unlearning Interference with Gradient Projection [56.292071534857946]
  Recent data-privacy laws have sparked interest in machine unlearning. Challenge is to discard information about the forget'' data without altering knowledge about remaining dataset. We adopt a projected-gradient based learning method, named as Projected-Gradient Unlearning (PGU) We provide empirically evidence to demonstrate that our unlearning method can produce models that behave similar to models retrained from scratch across various metrics even when the training dataset is no longer accessible.
  arXiv  Detail & Related papers  (2023-12-07T07:17:24Z)
• Forgettable Federated Linear Learning with Certified Data Unlearning [34.532114070245576]
  Federated Unlearning (FU) has emerged to address demands for the "right to be forgotten"" and unlearning of the impact of poisoned clients without requiring retraining in FL. Most FU algorithms require the cooperation of retained or target clients (clients to be unlearned), additional communication overhead and potential security risks. We present FedRemoval, a certified, efficient, and secure unlearning strategy that enables the server to unlearn a target client without requiring client communication or adding additional storage.
  arXiv  Detail & Related papers  (2023-06-03T23:53:57Z)
• Federated Unlearning: How to Efficiently Erase a Client in FL? [9.346673106489742]
  We propose a method to erase a client by removing the influence of their entire local data from the trained global model. Our unlearning method achieves comparable performance as the gold standard unlearning method of federated retraining from scratch. 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.
  arXiv  Detail & Related papers  (2022-07-12T13:24:23Z)
• Acceleration of Federated Learning with Alleviated Forgetting in Local Training [61.231021417674235]
  Federated learning (FL) enables distributed optimization of machine learning models while protecting privacy. We propose FedReg, an algorithm to accelerate FL with alleviated knowledge forgetting in the local training stage. Our experiments demonstrate that FedReg not only significantly improves the convergence rate of FL, especially when the neural network architecture is deep.
  arXiv  Detail & Related papers  (2022-03-05T02:31:32Z)
• Machine Unlearning of Features and Labels [72.81914952849334]
  We propose first scenarios for unlearning and labels in machine learning models. Our approach builds on the concept of influence functions and realizes unlearning through closed-form updates of model parameters.
  arXiv  Detail & Related papers  (2021-08-26T04:42:24Z)
• Toward Understanding the Influence of Individual Clients in Federated Learning [52.07734799278535]
  Federated learning allows clients to jointly train a global model without sending their private data to a central server. We defined a new notion called em-Influence, quantify this influence over parameters, and proposed an effective efficient model to estimate this metric.
  arXiv  Detail & Related papers  (2020-12-20T14:34:36Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.