Detection of Adversarial Attacks in Robotic Perception

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sharawy, Ziad, Nakshbandi, Mohammad, Grigorescu, Sorin Mihai
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908926149132288
author Sharawy, Ziad
Nakshbandi, Mohammad
Grigorescu, Sorin Mihai
author_facet Sharawy, Ziad
Nakshbandi, Mohammad
Grigorescu, Sorin Mihai
contents Deep 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.
format Preprint
id arxiv_https___arxiv_org_abs_2603_28594
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Detection of Adversarial Attacks in Robotic Perception
Sharawy, Ziad
Nakshbandi, Mohammad
Grigorescu, Sorin Mihai
Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
Robotics
Deep 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.
title Detection of Adversarial Attacks in Robotic Perception
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Cryptography and Security
Robotics
url https://arxiv.org/abs/2603.28594