3 papers
cs.CV2022
Towards Flexible Inductive Bias via Progressive Reparameterization Scheduling
Yunsung Lee, Gyuseong Lee, Kwangrok Ryoo +3
There are two de facto standard architectures in recent computer vision: Convolutional Neural Networks (CNNs) and Vision Transformers (ViTs). Strong inductive biases of convolution…
cs.CV2021
Geometrically Adaptive Dictionary Attack on Face Recognition
Junyoung Byun, Hyojun Go, Changick Kim
CNN-based face recognition models have brought remarkable performance improvement, but they are vulnerable to adversarial perturbations. Recent studies have shown that adversaries…
cs.CR2021
On the Effectiveness of Small Input Noise for Defending Against Query-based Black-Box Attacks
Junyoung Byun, Hyojun Go, Changick Kim
While deep neural networks show unprecedented performance in various tasks, the vulnerability to adversarial examples hinders their deployment in safety-critical systems. Many stud…