How adversarial attacks can disrupt seemingly stable accurate classifiers

Oliver J. Sutton(University of Leicester), Desmond J. Higham(Maxwell Institute for Mathematical Sciences), Qinghua Zhou(University of Leicester), Ivan Tyukin(Skolkovo Institute of Science and Technology), Alexander N. Gorban(University of Leicester), Alexander Bastounis(King's College London)
Neural Networks
September 12, 2024
Cited by 11


Related Papers