SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation

Computer Science > Computer Vision and Pattern Recognition [Submitted on 11 Aug 2026] SegPAR: Class-Centric Decision-Based Sparse Attack for Semantic Segmentation Dongsu Song, DaeYun GO, Boseung Seo, Jay Hoon Jung Despite the practical relevance of sparse decision-based black-box threats, they have received limited attention in semantic segmentation. To bridge this gap, we adapt the most representative decision-based black-box sparse attacks from the classification domain to serve as baselines, establishing a rigorous benchmark for this underexplored setting. In this context, we demonstrate that one of the existing methods suffers from severe query inefficiency due to its image-centric pixel accumulation, which rapidly exhausts query budgets across the vast image space. To overcome this, we propose SegPAR, a novel decision-based framework that shifts to a class-centric exploration paradigm. Furthermore, to eliminate the misleading feedback generated by standard decision rewards during pixel accumulation, we introduce a novel discrepancy reward. Extensive experiments show that SegPAR significantly outperforms black-box baselines in sparsity efficiency and MIoU reduction, while remaining competitive with white-box sparse attacks. Code is available at \href{this https URL}{this https URL}. Comments: ECCV 2026 poster Subjects: Computer Vision and Pattern Recognition (cs.CV); Artificial Intelligence (cs.AI); Cryptography and Security (cs.CR); Machine Learning (cs.LG) Cite as: arXiv:2608.11285 [cs.CV]   (or arXiv:2608.11285v1 [cs.CV] for this version)   https://doi.org/10.48550/arXiv.2608.11285 Focus to learn more Submission history From: Jay Hoon Jung [view email] [v1] Tue, 11 Aug 2026 14:44:33 UTC (6,325 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CV < prev   |   next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.CR cs.LG References & Citations NASA ADS Google Scholar Semantic Scholar Export BibTeX Citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer (What is the Explorer?) Connected Papers Toggle Connected Papers (What is Connected Papers?) Litmaps Toggle Litmaps (What is Litmaps?) scite.ai Toggle scite Smart Citations (What are Smart Citations?) Code, Data, Media Demos Related Papers About arXivLabs Which authors of this paper are endorsers? | Disable MathJax (What is MathJax?)