Increasing Neural-Based Pedestrian Detectors’ Robustness to Adversarial Patch Attacks Using Anomaly Localization

Increasing Neural-Based Pedestrian Detectors’ Robustness to Adversarial Patch Attacks Using Anomaly Localization

Object detection in images is a fundamental component of many safety-critical systems, such as autonomous driving, video surveillance systems, and robotics. Adversarial patch attacks, being easily implemented in the real world, provide effective counteraction to object detection by state-of-the-art...

Full description

Saved in:
Bibliographic Details
Main Authors: Olga Ilina, Maxim Tereshonok, Vadim Ziyadinov
Format: Article
Language:English
Published: MDPI AG 2025-01-01
Series:Journal of Imaging
Subjects:
adversarial patch attack
robustness
pedestrian detection
deep convolutional neural network
Online Access:https://www.mdpi.com/2313-433X/11/1/26
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/2313-433X/11/1/26

Similar Items