July 10, 2024, 4:18 a.m. | Yuxuan Zhu, Michael Mandulak, Kerui Wu, George Slota, Yuseok Jeon, Ka-Ho Chow, Lei Yu

cs.CR updates on arXiv.org arxiv.org

arXiv:2407.02431v2 Announce Type: replace-cross
Abstract: Graph Neural Networks (GNNs) are gaining popularity across various domains due to their effectiveness in learning graph-structured data. Nevertheless, they have been shown to be susceptible to backdoor poisoning attacks, which pose serious threats to real-world applications. Meanwhile, graph reduction techniques, including coarsening and sparsification, which have long been employed to improve the scalability of large graph computational tasks, have recently emerged as effective methods for accelerating GNN training on large-scale graphs. However, …

applications arxiv attacks backdoor cs.cr cs.lg data domains graph networks neural networks poisoning poisoning attacks real robustness serious structured data techniques threats world

Journeyman Software Developer

@ Leidos | 6314 Remote/Teleworker US

Customer Assurance Analyst

@ London Stock Exchange Group | POL-Gdynia-3T Office Park, Tower C

Risk Consulting - Protect Tech - Senior -ERP Controls

@ EY | Bengaluru, KA, IN, 560016

ITGC Senior

@ EY | Hyderabad, TG, IN, 500081

Technology Risk Officer

@ State Street | Quincy, Massachusetts

Sr. Risk Manager, Data Risk Governance

@ KeyBank | For Those Who Work At Home, OH