Detecting adversarial examples for deep neural networks via layer directed discriminative noise injection

• Main Authors: Wang, Si, Liu, Wenye, Chang, Chip-Hong
• Other Authors: School of Electrical and Electronic Engineering
• Format: Conference or Workshop Item
• Language: English
• Published: 2020
• Subjects: Engineering::Electrical and electronic engineering::Integrated circuits; Machine Learning Security; Adversarial Attack
• Online Access: https://hdl.handle.net/10356/137128; https://doi.org/10.21979/N9/WCIL7X
• Institution: Nanyang Technological University

Deep learning is a popular powerful machine learning solution to the computer vision tasks. The most criticized vulnerability of deep learning is its poor tolerance towards adversarial images obtained by deliberately adding imperceptibly small perturbations to the clean inputs. Such negatives can d...