Robust Physical-World Attacks on Deep Learning Visual Classification¶
Eykholt. (2018). Robust Physical-World Attacks on Deep Learning Visual Classification. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition.
Cited by¶
2 citations across 2 artifacts.
Each citation links to the sentence it supports in the citing article.
Domain-specific¶
- Input Manipulation Attack
- They applied a few black-and-white stickers to a real stop sign, arranged so a deep classifier read it as a "Speed Limit 45" sign — and, critically, the misclassification held across the range of viewing distances and angles a moving vehicle would encounter
This sourceEykholt et al.'s robust physical attack, in which black-and-white stickers on a real Stop sign make road-sign classifiers read it as Speed Limit 45 across widely varying distances and angles, including drive-by video from a moving vehicle.
SupportedVerified against a saved copy of the source
“our final form of perturbation is a set of black and white stickers that an adversary can attach to a physical road sign (Stop sign)”
- They applied a few black-and-white stickers to a real stop sign, arranged so a deep classifier read it as a "Speed Limit 45" sign — and, critically, the misclassification held across the range of viewing distances and angles a moving vehicle would encounter
- Nut Graf
- A machine-learning paper might open concretely — a self-driving car's vision system misreads a stop sign altered with a few stickers — giving the reader a vivid, specific stake
This sourceThe physical-attack result in which black-and-white stickers on a real stop sign cause a deep road-sign classifier to misclassify it.
Supported in partVerified against the publisher's abstract
“With a perturbation in the form of only black and white stickers, we attack a real stop sign, causing targeted misclassification in 100% of the images obtained in lab settings, and in 84.8% of the captured video frames obtained on a moving vehicle (field test) for the target classifier.”
- A machine-learning paper might open concretely — a self-driving car's vision system misreads a stop sign altered with a few stickers — giving the reader a vivid, specific stake
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 2 of 2 citations: 1 supported, 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:85635e3bfea4 · see in the full table