activity
20202023
most citedClass Attention Transfer Based Knowledge Distillation

6 citations · 14 across the 6 of their papers we have counts for

collaborators

6 papers

cs.LG2023

PAGE: Equilibrate Personalization and Generalization in Federated Learning

Qian Chen, Zilong Wang, Jiaqi Hu +3

Federated learning (FL) is becoming a major driving force behind machine learning as a service, where customers (clients) collaboratively benefit from shared local updates under th…

cs.CR2023★ 2 cited

RECESS Vaccine for Federated Learning: Proactive Defense Against Model Poisoning Attacks

Haonan Yan, Wenjing Zhang, Qian Chen +4

Model poisoning attacks greatly jeopardize the application of federated learning (FL). The effectiveness of existing defenses is susceptible to the latest model poisoning attacks,…

cs.CV2023★ 6 cited

Class Attention Transfer Based Knowledge Distillation

Ziyao Guo, Haonan Yan, Hui Li +1

Previous knowledge distillation methods have shown their impressive performance on model compression tasks, however, it is hard to explain how the knowledge they transferred helps…

cs.CR2022★ 1 cited

Dap-FL: Federated Learning flourishes by adaptive tuning and secure aggregation

Qian Chen, Zilong Wang, Jiawei Chen +2

Federated learning (FL), an attractive and promising distributed machine learning paradigm, has sparked extensive interest in exploiting tremendous data stored on ubiquitous mobile…

cs.CR2020★ 3 cited

Monitoring-based Differential Privacy Mechanism Against Query-Flooding Parameter Duplication Attack

Haonan Yan, Xiaoguang Li, Hui Li +3

Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through…

cs.CR2020★ 2 cited

Mitigating Query-Flooding Parameter Duplication Attack on Regression Models with High-Dimensional Gaussian Mechanism

Xiaoguang Li, Hui Li, Haonan Yan +3

Public intelligent services enabled by machine learning algorithms are vulnerable to model extraction attacks that can steal confidential information of the learning models through…