SSAP: A Shape-Sensitive Adversarial Patch for Comprehensive Disruption of Monocular Depth Estimation in Autonomous Navigation Applications

arXiv:2403.11515v1 Announce Type: new
Abstract: Monocular depth estimation (MDE) has advanced significantly, primarily through the integration of convolutional neural networks (CNNs) and more recently, Transformers. However, concerns about their susceptibility to adversarial attacks have emerged, especially in safety-critical domains like autonomous driving and robotic navigation. Existing approaches for assessing CNN-based depth prediction methods have fallen short in inducing comprehensive disruptions to the vision system, often limited to specific local areas. In this paper, we introduce SSAP (Shape-Sensitive Adversarial Patch), a …

abstract advanced adversarial adversarial attacks applications arxiv attacks autonomous autonomous driving cnns concerns convolutional neural networks cs.cv cs.ro disruption domains driving however integration mde navigation networks neural networks robotic safety safety-critical through transformers type