BROWSE
Detail
Conference Paper
Training-Free Traffic-Sign Detection Recovery via Open-Vocabulary Adversarial-Patch Localization
Cited - time in 
Share 
Share
- Authors
- Kangmin Bae, Hyunwoo Jin, Sungwon Yi
- Issue Date
- 2026-09
- Citation
- European Conference on Computer Vision (ECCV) 2026 Workshop : Safe and Defensive Autonomous Driving (SDAD), pp.1-9
- Publisher
- Safe and Defensive Autonomous Driving (SDAD)
- Language
- English
- Type
- Conference Paper
- Abstract
- Removing an adversarial patch is not equivalent to recovering the evidence required by an object detector. In traffic-sign images, a patch can occlude the class-defining symbol; a perceptually plausible completion may therefore depict the wrong sign, while unconstrained recovery may overwrite predictions that survived the attack. We study this distinction on REAP and propose a training-free recovery framework for settings in which detector retraining is unavailable. A frozen open-vocabulary detector hierarchically localizes candidate signs and patch regions without access to patch size, count, or placement. The resulting boxes define masks for native-resolution local inpainting. Detections from the recovered image and contextual crops are fused asymmetrically with an immutable attacked-image output, while a frozen visual-encoder ensemble supplies ranked class hypotheses from clean references. No detector, localizer, or encoder parameter is updated. This formulation separates open-vocabulary patch localization from privileged benchmark geometry and treats perceptual completion, semantic recovery, and detection preservation as distinct problems.
- Keyword
- Adversarial patches, Traffic sign detection, Training-free recovery, Image inpainting
- KSP Keywords
- Free recovery, Image Inpainting, Patch size, Traffic Sign Detection, object detector