cs.CVcs.AIcs.CRcs.RO
Detection of Adversarial Attacks in Robotic Perception
Mar 30, 2026(revised Mar 31, 2026)
AI Summarygemma4:e4b
This paper addresses the vulnerability of DNNs used in robotic semantic segmentation to adversarial attacks by proposing specialized detection strategies to enhance safety in robotic perception systems.
Abstract
More Like ThisDeep Neural Networks (DNNs) achieve strong performance in semantic segmentation for robotic perception but remain vulnerable to adversarial attacks, threatening safety-critical applications. While robustness has been studied for image classification, semantic segmentation in robotic contexts requires specialized architectures and detection strategies.