9 citations · 27 across the 13 of their papers we have counts for
4 papers · 1 filter
FedMID: A Data-Free Method for Using Intermediate Outputs as a Defense Mechanism Against Poisoning Attacks in Federated Learning
Sungwon Han, Hyeonho Song, Sungwon Park +1
Federated learning combines local updates from clients to produce a global model, which is susceptible to poisoning attacks. Most previous defense strategies relied on vectors deri…
Generating High-Resolution Regional Precipitation Using Conditional Diffusion Model
Naufal Shidqi, Chaeyoon Jeong, Sungwon Park +3
Climate downscaling is a crucial technique within climate research, serving to project low-resolution (LR) climate data to higher resolutions (HR). Previous research has demonstrat…
Towards Attack-tolerant Federated Learning via Critical Parameter Analysis
Sungwon Han, Sungwon Park, Fangzhao Wu +4
Federated learning is used to train a shared model in a decentralized way without clients sharing private data with each other. Federated learning systems are susceptible to poison…
A Comprehensive Approach to Unsupervised Embedding Learning based on AND Algorithm
Sungwon Han, Yizhan Xu, Sungwon Park +2
Unsupervised embedding learning aims to extract good representation from data without the need for any manual labels, which has been a critical challenge in many supervised learnin…