Zobrazeno 1 - 2
of 2
pro vyhledávání: '"Mandulak, Michael"'
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
Externí odkaz:
http://arxiv.org/abs/2407.02431
Autor:
Kang, Inwon1,2 (AUTHOR) kangi@rpi.edu, Mandulak, Michael1,2 (AUTHOR), Szymanski, Boleslaw K.1,2,3 (AUTHOR) szymab@rpi.edu
Publikováno v:
Scientific Reports. 12/17/2022, Vol. 12 Issue 1, p1-15. 15p.
