<ul><li>Deep neural networks (DNNs) are susceptible to Universal Adversarial Perturbations (UAPs) that can deceive a target model across a wide range of samples.</li><li>In this paper, a novel data-free method called Intrinsic UAP (IntriUAP) is proposed to attack deep models without using any image samples.</li><li>The vulnerability of deep models is predominantly influenced by the linear components, which are leveraged in IntriUAP to achieve highly competitive performance in attacking popular image classification deep models.</li><li>The method also demonstrates strong black-box attack performance even with limited access to the victim model's layers.</li></ul>

Data-Free Universal Attack by Exploiting the Intrinsic Vulnerability of Deep Models

Discover more