Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection

Computer Science > Computer Vision and Pattern Recognition [Submitted on 16 Jun 2026] Budget-Aware Adaptive Adversarial Patches for Black-Box Object Detection Pedram MohajerAnsari, Amir Salarpour, David Fernandez, Mert D. Pesé Adversarial patches pose a practical threat to modern object detectors. Prior work shows vulnerability, but three gaps limit actionable insight: (i) few \emph{score-based black-box} attacks \emph{jointly} optimize patch \emph{location, texture, and size} under tight query budgets; (ii) success is rarely tied to the patch's \emph{visual footprint}; and (iii) evaluations often conflate EOT robustness with plain-view suppression. We present \method{}, a query-efficient, budget-adaptive black-box attack that couples a lightweight \emph{Contextual Thompson-Sampling} placer with NES-style pixel updates, growing the patch only when progress stalls. Reporting is anchored by a \emph{strict plain-image} suppression test; EOT is audited but never used as a substitute for success, and optional appearance/printability weights expose strength--visibility trade-offs. Across YOLOv5, Faster R-CNN, and YOLOS, \method{} achieves strong suppression on CNN-based detectors and substantial suppression on the transformer-based detector, using compact patches and exposing clear query--footprint trade-offs relative to fixed-size and heuristic baselines. A print--capture pilot further shows transfer across unseen physical objects and viewpoints. Comments: Accepted to the 2026 IEEE International Conference on Image Processing (ICIP 2026) Subjects: Computer Vision and Pattern Recognition (cs.CV); Cryptography and Security (cs.CR) Cite as: arXiv:2606.18318 [cs.CV]   (or arXiv:2606.18318v1 [cs.CV] for this version)   https://doi.org/10.48550/arXiv.2606.18318 Focus to learn more Submission history From: Pedram MohajerAnsari [view email] [v1] Tue, 16 Jun 2026 13:38:15 UTC (4,324 KB) Access Paper: HTML (experimental) view license Current browse context: cs.CV < prev   |   next > new | recent | 2026-06 Change to browse by: cs cs.CR 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?)