Adversarial Patches for Fooling Positive–Negative Obstacle Detectors on Unstructured Roads
- 15 July 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (19) , 36466-36478
Abstract
Adversarial patches represent a critical form of physical adversarial attacks, posing significant risks to the security of neural network-based object detection systems. Previous research on adversarial patches has predominantly focused on pedestrian detection, facial recognition, and vehicle detection, with limited attention to the detection of positive and negative obstacles on unstructured roads. Moreover, prior studies typically optimize perturbation information while fixing parameters such as the patch’s position and rotation angle, or manipulate parameters such as position and rotation angle while fixing the perturbation information to generate adversarial patches. In this context, we propose a PRP multi-adversarial patch attack method based on a simulated annealing improved differential evolution algorithm (SADE-PRP), designed to deceive unstructured positive and negative obstacle detection systems. Firstly, We propose a PRP-guided multi-adversarial patch framework for visible light-based positive-negative obstacle detection systems. This framework simultaneously considers three features of the adversarial patch: position, rotation angle and perturbation pixels, as opposed to manually setting these parameters like most previous works. Secondly, we employ more robust based simulated annealing improved differential evolution algorithm (SADE), which effectively improved the robustness, achieving higher attack success rates in black-box attack scenarios. Finally, we constructed a dataset of positive-negative obstacles on unstructured roads. Then, we conducted extensive experiments in both digital and physical environments to demonstrate the superiority of the proposed method.Keywords
Funding Information
- Guangxi science and technology major project (Guike AA23023011, Guike AA23062040)
- National Natural Science Foundation Project (52365001)
- Guangxi Key Research and Development Project (Guike AB22080098)
This publication has 41 references indexed in Scilit:
- Two-stage optimized unified adversarial patch for attacking visible-infrared cross-modal detectors in the physical worldApplied Soft Computing, 2025
- Pothole detection‐you only look once: Deformable convolution based road pothole detectionIET Image Processing, 2024
- Fooling human detectors via robust and visually natural adversarial patchesNeurocomputing, 2024
- Few pixels attacks with generative modelPattern Recognition, 2023
- Design and Interpretation of Universal Adversarial Patches in Face Detection2020
- End-to-End Object Detection with Transformers2020
- Universal Physical Camouflage Attacks on Object Detectors2020
- Threat of Adversarial Attacks on Deep Learning in Computer Vision: A SurveyIEEE Access, 2018
- You Only Look Once: Unified, Real-Time Object Detection2016
- Particle swarm optimizationSwarm Intelligence, 2007