mlsanityData to 7 Oct 2026

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

arXiv 2606.18318 ↗First posted 16 Jun 2026cs.CV cs.CRcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial patches pose a practical threat to modern object detectors. Prior work shows vulnerability, but three gaps limit actionable insight: (i) few score-based black-box attacks jointly optimize patch location, texture, and size under tight query budgets; (ii) success is rarely tied to the patch's 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 Contextual Thompson-Sampling placer with NES-style pixel updates, growing the patch only when progress stalls. Reporting is anchored by a 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.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 18 of its 20 references that are in the map. First posted on arXiv 16 Jun 2026.

Builds on

18 of 20 references.

References · 18

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2013Intriguing properties of neural networkscited by 5,114
  3. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,829
  4. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  5. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 656
  6. 2017Adversarial Patchcited by 514
  7. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 499
  8. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  9. 2021You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detectioncited by 170
  10. 2018DPatch: An Adversarial Patch Attack on Object Detectorscited by 146
  11. 2018Prior Convictions: Black-Box Adversarial Attacks with Bandits and Priorscited by 145
  12. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
6 more
  1. 2022Parallel Rectangle Flip Attack: A Query-based Black-box Attack against Object Detectioncited by 79
  2. 2020PatchAttack: A Black-box Texture-based Attack with Reinforcement Learningcited by 67
  3. 2020The Translucent Patch: A Physical and Universal Attack on Object Detectorscited by 62
  4. 2022Simultaneously Optimizing Perturbations and Positions for Black-box Adversarial Patch Attackscited by 41
  5. 2023Patch of Invisibility: Naturalistic Physical Black-Box Adversarial Attacks on Object Detectorscited by 5
  6. 2024BB-Patch: BlackBox Adversarial Patch-Attack using Zeroth-Order Optimizationcited by 2

Built on by

Not cited yet.