all InfoSec news
Revisiting Edge Perturbation for Graph Neural Network in Graph Data Augmentation and Attack
March 14, 2024, 4:11 a.m. | Xin Liu, Yuxiang Zhang, Meng Wu, Mingyu Yan, Kun He, Wei Yan, Shirui Pan, Xiaochun Ye, Dongrui Fan
cs.CR updates on arXiv.org arxiv.org
Abstract: Edge perturbation is a basic method to modify graph structures. It can be categorized into two veins based on their effects on the performance of graph neural networks (GNNs), i.e., graph data augmentation and attack. Surprisingly, both veins of edge perturbation methods employ the same operations, yet yield opposite effects on GNNs' accuracy. A distinct boundary between these methods in using edge perturbation has never been clearly defined. Consequently, inappropriate perturbations may lead to undesirable …
arxiv attack augmentation basic can cs.cr cs.lg data edge graph network networks neural network neural networks performance
More from arxiv.org / cs.CR updates on arXiv.org
Jobs in InfoSec / Cybersecurity
Incident Response Lead
@ Blue Yonder | Hyderabad
GRC Analyst
@ Chubb | Malaysia
Information Security Manager
@ Walbec Group | Waukesha, WI, United States
Senior Executive / Manager, Security Ops (TSSQ)
@ SMRT Corporation Ltd | Singapore, SG
Senior Engineer, Cybersecurity
@ Sonova Group | Valencia (CA), United States
Consultant (Multiple Positions Available)
@ Atos | Plano, TX, US, 75093