Federated Unlearning via Class-Discriminative Pruning

Wang, Junxiao; Guo, Song; Xie, Xin; Qi, Heng

doi:10.1145/3485447.3512222

Cited by 34 publications

(15 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For deep neural networks, Golatkar, Achille, and Soatto (2020) try to add a fisher noise to hide the information about unlearn data. The work closest to ours is (Wang et al 2022) (which is a concurrent work). They try to scrub memories for each category in federated learning.…”

Section: Related Workmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

Graphs can model complex relationships between objects, enabling a myriad of Web applications such as online page/article classification and social recommendation. While graph neural networks (GNNs) have emerged as a powerful tool for graph representation learning, in an end-to-end supervised setting, their performance heavily relies on a large amount of task-specific supervision. To reduce labeling requirement, the "pre-train, fine-tune" and "pre-train, prompt" paradigms have become increasingly common. In particular, prompting is a popular alternative to fine-tuning in natural language processing, which is designed to narrow the gap between pre-training and downstream objectives in a task-specific manner. However, existing study of prompting on graphs is still limited, lacking a universal treatment to appeal to different downstream tasks. In this paper, we propose GraphPrompt, a novel pre-training and prompting framework on graphs. GraphPrompt not only unifies pre-training and downstream tasks into a common task template, but also employs a learnable prompt to assist a downstream task in locating the most relevant knowledge from the pre-trained model in a task-specific manner. Finally, we conduct extensive experiments on five public datasets to evaluate and analyze GraphPrompt. CCS CONCEPTS• Computing methodologies → Learning latent representations; • Information systems → Data mining.

show abstract

Section: Related Workmentioning

confidence: 99%

Geography of Technology Transfer in China

Liu

2023

East China Normal University Scientific Reports

View full text Add to dashboard Cite

show abstract

“…We often consider backdoor attacks as a great threat in FL while ignoring its potential advantages. Indeed, a backdoor attack demonstrated its sake under the unlearning scenario, which is a technique in FL [28,128,129] focusing on removing or revoking access to data, participants, or parts of the model, with the goal of improving the integrity and accuracy of the model. Backdoor triggers are utilized as an evaluation tool to assess the effectiveness of unlearning methods [130].…”

Section: Discussionmentioning

confidence: 99%

Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions

Nguyen¹,

Nguyen²,

Nguyen³

et al. 2023

Preprint

View full text Add to dashboard Cite

Federated learning (FL) is a machine learning (ML) approach that allows the use of distributed data without compromising personal privacy. However, the heterogeneous distribution of data among clients in FL can make it difficult for the orchestration server to validate the integrity of local model updates, making FL vulnerable to various threats, including backdoor attacks. Backdoor attacks involve the insertion of malicious functionality into a targeted model through poisoned updates from malicious clients. These attacks can cause the global model to misbehave on specific inputs while appearing normal in other cases. Backdoor attacks have received significant attention in the literature due to their potential to impact real-world deep learning applications. However, they have not been thoroughly studied in the context of FL. In this survey, we provide a comprehensive survey of current backdoor attack strategies and defenses in FL, including a comprehensive analysis of different approaches. We also discuss the challenges and potential future directions for attacks and defenses in the context of FL.

show abstract

“…The simple models such as linear and logistic regression [4,5,6,7], ran-dom forests [8], and k-means clustering [9,10] have been explored in an provable unlearning setup. Furthermore, the deep learning models such as convolutional neural networks [11,12,13,14,15,16] and vision transformers [17] have been explored with approximate unlearning setup. All these existing methods are aimed at unlearning in classification problems.…”

Section: Motivationmentioning

confidence: 99%

“…This approach allows the model owner to enable or disable the information of certain tasks or samples at multiple instances. Several works have presented efficient methods for unlearning in federated learning setup [14,31,32]. Bevan and Abarghouei [33] use the bias unlearning methods [34] to remove bias from CNN based melanoma classification.…”

Section: Related Workmentioning

confidence: 99%

Deep Regression Unlearning

Tarun¹,

Chundawat²,

Mandal³

et al. 2022

Preprint

View full text Add to dashboard Cite

With the introduction of data protection and privacy regulations, it has become crucial to remove the lineage of data on demand in a machine learning system. In past few years, there has been notable development in machine unlearning to remove the information of certain training data points efficiently and effectively from the model. In this work, we explore unlearning in a regression problem, particularly in deep learning models. Unlearning in classification and simple linear regression has been investigated considerably. However, unlearning in deep regression models largely remain an untouched problem till now. In this work, we introduce deep regression unlearning methods that are well generalized and robust to privacy attacks. We propose the Blindspot unlearning method which uses a novel weight optimization process. A randomly initialized model, partially exposed to the retain samples and a copy of original model are used together to selectively imprint knowledge about the data that we wish to keep and scrub the information of the data we wish to forget. We also propose a Gaussian distribution based fine tuning method for regression unlearning. The existing evaluation metrics for unlearning in a classification task are not directly applicable for regression unlearning. Therefore, we adapt these metrics for regression task. We devise a membership inference attack to check the privacy leaks in the unlearned regression model. We conduct the experiments on regression tasks for computer vision, natural language processing and forecasting applications. Our deep regression unlearning methods show excellent performance across all of these datasets and metrics.

show abstract

Federated Unlearning via Class-Discriminative Pruning

Cited by 34 publications

References 18 publications

Geography of Technology Transfer in China

Geography of Technology Transfer in China

Backdoor Attacks and Defenses in Federated Learning: Survey, Challenges and Future Research Directions

Deep Regression Unlearning

Contact Info

Product

Resources

About