Remove To Regenerate: Boosting Adversarial Generalization with Attack Invariance

X Fu, L Ma, L Zhang - … Transactions on Circuits and Systems for …, 2024 - ieeexplore.ieee.org
Adversarial attacks pose a huge challenge to the deployment of deep neural networks
(DNNs) in security-sensitive applications. Adversarial defense methods are developed to …

[PDF][PDF] ATKSCOPES: Multiresolution Adversarial Perturbation as a Unified Attack on Perceptual Hashing and Beyond

Y Zhang, Y Sun, S Qi, Z Hua, W Wen, Y Fang - shurenqi.github.io
Privacy and regulation are a long-lasting conflict in modern instant messaging, where the
security community attempts to bridge this gap from a technological perspective. End-to-end …