Defend Against Adversarial Samples by Using Perceptual Hash
Changrui Liu, Dengpan Ye, Yueyun Shang, Shunzhi Jiang, Shiyu Li, Yuan Mei, Liqiang Wang · Computers, materials & continua/Computers, materials & continua (Print) · 2020
Image classifiers that based on Deep Neural Networks (DNNs) have been proved to be easily fooled by well-designed perturbations. Previous defense methods have the limitations of requiring expensive computation or reducing... | Find, read and cite all the research you need on Tech Science Press