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

• المؤلفون الرئيسيون: Wang, Si, Liu, Wenye, Chang, Chip-Hong
• مؤلفون آخرون: School of Electrical and Electronic Engineering
• التنسيق: Conference or Workshop Item
• اللغة: English
• منشور في: 2020
• الموضوعات: Engineering::Electrical and electronic engineering::Computer hardware, software and systems; Deep Learning Security; Adversarial Attack
• الوصول للمادة أونلاين: https://hdl.handle.net/10356/144346; https://doi.org/10.21979/N9/YPY0EB

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...