PNAP-YOLO: An Improved Prompts-Based Naturalistic Adversarial Patch Model for Object Detectors

Jun Li (), Chenwu Shan, Liyan Shen, Yawei Ren and Jiajie Zhang
Additional contact information
Jun Li: Beijing Information Science and Technology University
Chenwu Shan: Beijing Information Science and Technology University
Liyan Shen: Beijing Information Science and Technology University
Yawei Ren: Beijing Information Science and Technology University
Jiajie Zhang: Beijing Information Science and Technology University

Annals of Data Science, 2025, vol. 12, issue 3, No 11, 1055-1072

Abstract: Abstract Detectors have been extensively utilized in various scenarios such as autonomous driving and video surveillance. Nonetheless, recent studies have revealed that these detectors are vulnerable to adversarial attacks, particularly adversarial patch attacks. Adversarial patches are specifically crafted to disrupt deep learning models by disturbing image regions, thereby misleading the deep learning models when added to into normal images. Traditional adversarial patches often lack semantics, posing challenges in maintaining concealment in physical world scenarios. To tackle this issue, this paper proposes a Prompt-based Natural Adversarial Patch generation method, which creates patches controllable by textual descriptions to ensure flexibility in application. This approach leverages the latest text-to-image generation model—Latent Diffusion Model (LDM) to produce adversarial patches. We optimize the attack performance of the patches by updating the latent variables of LDM through a combined loss function. Experimental results indicate that our method can generate more natural, semantically rich adversarial patches, achieving effective attacks on various detectors.

Keywords: Object detector; Diffusion model; Adversarial patch; Image generation (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s40745-025-00604-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:aodasc:v:12:y:2025:i:3:d:10.1007_s40745-025-00604-0

Ordering information: This journal article can be ordered from
https://www.springer ... gement/journal/40745

DOI: 10.1007/s40745-025-00604-0

Access Statistics for this article

Annals of Data Science is currently edited by Yong Shi

More articles in Annals of Data Science from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().