EUVIMEDOpdag EUVIMED
Open access · CC BY 4.0

WBA: Weather Backdoor Attack on Semantic Segmentation in the Internet of Things

Qiuhua Wang, Haojie Shen, Yijia Li, Yi Hu, Yizhi Ren, Gaoning Pan, Yanyu Cheng, Mingde Hu, Weizhi Meng

ACM Transactions on Internet of Things · 2026-11-30 · 7 (4) · 1-25

DOI: 10.1145/3800940 ↗

At a glance

Journal article in ACM Transactions on Internet of Things, published online on 2026-05-22. Written by Qiuhua Wang and 8 co-authors. 44 references. The full text is freely available (open access, CC BY 4.0). Funded by: “Pioneer” and “Leading Goose” Research and Development Program of Zhejiang, National Natural Science Foundation of China, Zhejiang Provincial Key Laboratory for Sensitive Data Security Protection and Confidentiality Management.

AbstractBibliografiske oplysningerCiteRelated studies

Abstract (original language)

As an important technology of computer vision, semantic segmentation is widely used in the Internet of Things (IoT), such as autonomous driving, intelligent healthcare, and Electronic Travel Aids (ETAs). It can segment the images captured by the IoT devices into different semantic areas, thereby helping them to more accurately understand image content and achieve more intelligent control and application. The security of semantic segmentation models directly affects the security of the IoT applications, especially when used for important security tasks. If attackers can control the model’s output, it will bring catastrophic consequences, even casualties. We propose a backdoor attack method against semantic segmentation models, the Weather Backdoor Attack (WBA). In our method, we innovatively propose to use weather features as triggers, which not only improves the stealthiness of triggers, but also achieves a high attack success rate. The experimental results show that our proposed WBA method can attack the semantic segmentation model with a high success rate by poisoning only a small portion of the training data. Under the settings of different victim classes, target classes, and various weather conditions, our proposed WBA method can also maintain the effectiveness of attacks. Meanwhile, due to the fact that the trigger we designed in this article simulates real-world weather conditions, it also has higher stealthiness.

Funding

  • “Pioneer” and “Leading Goose” Research and Development Program of Zhejiang
  • National Natural Science Foundation of China
  • Zhejiang Provincial Key Laboratory for Sensitive Data Security Protection and Confidentiality Management
  • Hangzhou Institute for Advanced Study, UCAS’s Independently Initiated Research Project

Cite

APA

Wang, Q., Shen, H., Li, Y., Hu, Y., Ren, Y., Pan, G., Cheng, Y., Hu, M., & Meng, W. (2026). WBA: Weather Backdoor Attack on Semantic Segmentation in the Internet of Things. ACM Transactions on Internet of Things, 7(4), 1-25. https://doi.org/10.1145/3800940

Vancouver

Wang Q, Shen H, Li Y, Hu Y, Ren Y, Pan G, et al. WBA: Weather Backdoor Attack on Semantic Segmentation in the Internet of Things. ACM Transactions on Internet of Things. 2026;7(4):1-25. doi:10.1145/3800940

BibTeX
@article{Wang2026,
  author = {Wang, Qiuhua and Shen, Haojie and Li, Yijia and Hu, Yi and Ren, Yizhi and Pan, Gaoning and Cheng, Yanyu and Hu, Mingde and Meng, Weizhi},
  title = {WBA: Weather Backdoor Attack on Semantic Segmentation in the Internet of Things},
  journal = {ACM Transactions on Internet of Things},
  year = {2026},
  volume = {7},
  number = {4},
  pages = {1--25},
  doi = {10.1145/3800940}
}
Start for free →