# Detection of Adversarial Attacks in Robotic Perception

Source: [Detection of Adversarial Attacks in Robotic Perception](<https://www.sota2.com/research/paper/69cb55840636e5bf4afca464>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-02T05:00:12.805Z

Authors: Ziad Sharawy, Mohammad Nakshbandi, Sorin Mihai Grigorescu

Published: 2026-03-30T15:41:49.000Z

## 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.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2603.28594>)

[PDF](<https://arxiv.org/pdf/2603.28594.pdf>)