Stable neural ODE with Lyapunov-stable equilibrium points for defending against adversarial attacks

• Main Authors: Kang, Qiyu, Song, Yang, Ding, Qinxu, Tay, Wee Peng
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2023
• Subjects: Engineering::Computer science and engineering::Computing methodologies::Artificial intelligence; Deep Neural Networks; Adversarial Attacks
• Online Access: https://hdl.handle.net/10356/166692; https://nips.cc/Conferences/2021; https://proceedings.neurips.cc/
• Institution: Nanyang Technological University

Deep neural networks (DNNs) are well-known to be vulnerable to adversarial attacks, where malicious human-imperceptible perturbations are included in the input to the deep network to fool it into making a wrong classification. Recent studies have demonstrated that neural Ordinary Differential Equati...