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

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 (2026) WBA : Weather Backdoor Attack on Semantic Segmentation in the Internet of Things. ACM Transactions on Internet of Things. ISSN 2691-1914

Abstract

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 weather backdoor attack 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 factthat the trigger we designed in this paper simulates real-world weather conditions, it also has higher stealthiness.