Impact of Architectural Modifications on Deep Learning Adversarial Robustness

arXiv:2405.01934v1 Announce Type: cross
Abstract: Rapid advancements of deep learning are accelerating adoption in a wide variety of applications, including safety-critical applications such as self-driving vehicles, drones, robots, and surveillance systems. These advancements include applying variations of sophisticated techniques that improve the performance of models. However, such models are not immune to adversarial manipulations, which can cause the system to misbehave and remain unnoticed by experts. The frequency of modifications to existing deep learning models necessitates thorough analysis to determine …

adoption advancements adversarial applications arxiv critical cs.ai cs.cr cs.cv cs.lg deep learning driving drones immune impact modifications performance rapid robots robustness safety safety-critical self-driving surveillance systems techniques vehicles