From Attack to Defense: Insights into Deep Learning Security Measures in Black-Box Settings

arXiv:2405.01963v1 Announce Type: cross
Abstract: Deep Learning (DL) is rapidly maturing to the point that it can be used in safety- and security-crucial applications. However, adversarial samples, which are undetectable to the human eye, pose a serious threat that can cause the model to misbehave and compromise the performance of such applications. Addressing the robustness of DL models has become crucial to understanding and defending against adversarial attacks. In this study, we perform comprehensive experiments to examine the effect of …

abstract adversarial applications arxiv box cs.ai cs.cr cs.cv cs.lg deep learning defense however human human eye insights safety samples security threat type