Fooling Automated Surveillance Cameras¶
Thys, Ranst, & Goedeme. (2019). Fooling Automated Surveillance Cameras: Adversarial Patches to Attack Person Detection. 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW).
Cited by¶
1 citation across 1 artifact.
Each citation links to the sentence it supports in the citing article.
Domain-specific¶
- Input Manipulation Attack
- Adversarial examples in vision — imperceptible pixel perturbations (Szegedy, Goodfellow) that flip a confident image-classification label while looking unchanged to a human. Adversarial patches — physical-world stickers or printed patterns (Brown et al.) that cause object detectors to misclassify or miss objects when the patch is in the camera frame
This sourceReports a printable person-detection patch that hides a person from a detector, holding up both in camera-filmed tests and in quantitative evaluation.
Supported in partVerified against the work's full text
“The goal is to generate a patch that is able successfully hide a person from a person detector.”
- Adversarial examples in vision — imperceptible pixel perturbations (Szegedy, Goodfellow) that flip a confident image-classification label while looking unchanged to a human. Adversarial patches — physical-world stickers or printed patterns (Brown et al.) that cause object detectors to misclassify or miss objects when the patch is in the camera frame
Verification¶
Does it exist? Not checked yet. This work's DOI is recorded above but has not been resolved against an external catalogue, so nothing here confirms the work exists.
Does it back the claim? Read against the text for 1 of 1 citation: 1 supported in part. Each verdict is shown under its citation below, with what in the work backs the sentence.
Support is checked per citation rather than per work — the same source can be cited soundly in one article and wrongly in another. Per-citation recording began recently, so a citation with no recorded check is a gap in the record rather than evidence it went unchecked.
See how references were verified.
Registry ID ref:04b49bad277d · see in the full table