Fired neuron rate based decision tree for detection of adversarial examples in DNNs

• Main Authors: Wang, Si, Liu, Wenye, Chang, Chip-Hong
• 其他作者: School of Electrical and Electronic Engineering
• 格式: Conference or Workshop Item
• 語言: English
• 出版: 2020
• 主題: Engineering::Electrical and electronic engineering::Computer hardware, software and systems; Deep Learning Security; Adversarial Attack
• 在線閱讀: https://hdl.handle.net/10356/144346; https://doi.org/10.21979/N9/YPY0EB
• 機構: Nanyang Technological University

Deep neural network (DNN) is a prevalent machine learning solution to computer vision problems. The most criticized vulnerability of deep learning is its susceptibility towards adversarial images crafted by maliciously adding infinitesimal distortions to the benign inputs. Such negatives can fool a...