Výsledky vyhledávání - "Lee, Younghan"

Report

VFLIP: A Backdoor Defense for Vertical Federated Learning via Identification and Purification

Autor: Cho, Yungi, Han, Woorim, Yu, Miseon, Lee, Younghan, Bae, Ho, Paek, Yunheung

Vertical Federated Learning (VFL) focuses on handling vertically partitioned data over FL participants. Recent studies have discovered a significant vulnerability in VFL to backdoor attacks which specifically target the distinct characteristics of VF

Externí odkaz: http://arxiv.org/abs/2408.15591

Zobrazit plný text záznamu

Report

Precise Extraction of Deep Learning Models via Side-Channel Attacks on Edge/Endpoint Devices

Autor: Lee, Younghan, Jun, Sohee, Cho, Yungi, Han, Woorim, Moon, Hyungon, Paek, Yunheung

With growing popularity, deep learning (DL) models are becoming larger-scale, and only the companies with vast training datasets and immense computing power can manage their business serving such large models. Most of those DL models are proprietary

Externí odkaz: http://arxiv.org/abs/2403.02870

Zobrazit plný text záznamu

Report

FLGuard: Byzantine-Robust Federated Learning via Ensemble of Contrastive Models

Autor: Lee, Younghan, Cho, Yungi, Han, Woorim, Bae, Ho, Paek, Yunheung

Federated Learning (FL) thrives in training a global model with numerous clients by only sharing the parameters of their local models trained with their private training datasets. Therefore, without revealing the private dataset, the clients can obta

Externí odkaz: http://arxiv.org/abs/2403.02846

Zobrazit plný text záznamu

Akademický článek

Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.

Akademický článek

Mega versus local event sponsorships

Autor: Koo, Jakeun, Fink, Janet S., Lee, Younghan

Publikováno v: Marketing Intelligence & Planning, 2022, Vol. 40, Issue 5, pp. 671-689.

Externí odkaz: http://www.emeraldinsight.com/doi/10.1108/MIP-11-2021-0392

Zobrazit plný text záznamu

Report

Extended Abstract: Mimicry Resilient Program Behavior Modeling with LSTM based Branch Models

Autor: Yi, Hayoon, Kim, Gyuwan, Lee, Jangho, Ahn, Sunwoo, Lee, Younghan, Yoon, Sungroh, Paek, Yunheung

In the software design, protecting a computer system from a plethora of software attacks or malware in the wild has been increasingly important. One branch of research to detect the existence of attacks or malware, there has been much work focused on

Externí odkaz: http://arxiv.org/abs/1803.09171

Zobrazit plný text záznamu