Kavli Affiliate: Dan Luo | First 5 Authors: Eashan Adhikarla, Dan Luo, Brian D. Davison, , | Summary: Many deep neural networks are susceptible to minute perturbations of images that have been carefully crafted to cause misclassification. Ideally, a robust classifier would be immune to small variations in input images, and a number of defensive […]
Continue.. Memory Defense: More Robust Classification via a Memory-Masking Autoencoder