Two-stage uncertainty-aware adversarial patch attack for semantic segmentation

作者：Jin Li, Haoze Wu, Yawei Ren, Jianyi Zhang, Liyan Shen · 发表于：International Journal of Intelligent Computing and Cybernetics · 年份：2026 · DOI：10.1108/ijicc-11-2025-0774 · 被引用次数：1 · 研究领域：Adversarial Robustness in Machine Learning、Advanced Neural Network Applications、Digital Media Forensic Detection

Purpose This work aims to investigate and improve adversarial patch attacks for semantic segmentation, a task increasingly deployed in security-critical applications. Existing attacks often overlook pixel-level uncertainty and spatial variation, resulting in inefficient optimization and limited effectiveness. The purpose of this study is to design an uncertainty-aware attack framework that better identifies and exploits structurally vulnerable regions in segmentation models. Design/methodology/approach We propose a two-stage uncertainty-aware adversarial patch attack framework. The first stage computes pixel-wise entropy to identify locally uncertain regions. The second stage applies a confidence-based inter-pixel weighting strategy that prioritizes vulnerable pixels by comparing their confidence to a global statistical threshold. These components are unified into a dynamic loss reweighting mechanism. Experiments are conducted on Cityscapes and BDD100 K using ICNet, DDRNet, and SegFormer. Findings Experimental results show that the proposed method outperforms existing patch-based attacks such as SSAP. By effectively targeting uncertain and structurally vulnerable regions, our method achieves stronger degradation of segmentation performance, with mIoU reduced to as low as 8%. The results demonstrate both high attack effectiveness and strong cross-dataset and cross-model generalization. Originality/value This work is the first to incorporate pixel-level uncertainty into adversa...