Work

Detection of Adversarial Attacks in Robotic Perception

Year: 2026

Type: preprint

Abstract: 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.

Source: arXiv (Cornell University)

DOI: 10.48550/arxiv.2603.28594

Authors: Sharawy, Ziad, Nakshbandi, Mohammad, Grigorescu, Sorin Mihai

Institutions: Transylvania University of Brașov, Robotics Research (United States), Transylvania University

Topic: Adversarial Robustness in Machine Learning

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: green

OpenAlex ID: W7147534388

Cites:

Cited by:

Related to: