Výsledky vyhledávání - "WANG, Guohong"

Report

One-to-Multiple Clean-Label Image Camouflage (OmClic) based Backdoor Attack on Deep Learning

Autor: Wang, Guohong, Ma, Hua, Gao, Yansong, Abuadbba, Alsharif, Zhang, Zhi, Kang, Wei, Al-Sarawib, Said F., Zhang, Gongxuan, Abbott, Derek

Image camouflage has been utilized to create clean-label poisoned images for implanting backdoor into a DL model. But there exists a crucial limitation that one attack/poisoned image can only fit a single input size of the DL model, which greatly inc

Externí odkaz: http://arxiv.org/abs/2309.04036

Zobrazit plný text záznamu

Akademický článek

Detection of hypersonic weak targets by high pulse repetition frequency radar based on multi‐hypothesis fuzzy‐matching radon transform

Autor: Wu Wei, Liu Dandan, Wang Guohong

Publikováno v: IET Radar, Sonar & Navigation, Vol 18, Iss 3, Pp 423-433 (2024)

Abstract For the integration detection of near space hypersonic weak targets by high pulse repetition frequency (PRF) radar, a novel method named Multi‐Hypothesis Fuzzy‐Matching Radon transform (MHFM‐RT) is proposed for the near space hypersoni

Externí odkaz: https://doaj.org/article/8db8914285aa44a0ac2a2e5008aab3c3

Zobrazit plný text záznamu

Report

SEDML: Securely and Efficiently Harnessing Distributed Knowledge in Machine Learning

Autor: Gao, Yansong, Li, Qun, Zheng, Yifeng, Wang, Guohong, Wei, Jiannan, Su, Mang

Training high-performing deep learning models require a rich amount of data which is usually distributed among multiple data sources in practice. Simply centralizing these multi-sourced data for training would raise critical security and privacy conc

Externí odkaz: http://arxiv.org/abs/2110.13499

Zobrazit plný text záznamu