REVIEW 1 cited by
Minority Reports Defense: Defending Against Adversarial Patches
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
Signed reviews
read the original abstract
Deep learning image classification is vulnerable to adversarial attack, even if the attacker changes just a small patch of the image. We propose a defense against patch attacks based on partially occluding the image around each candidate patch location, so that a few occlusions each completely hide the patch. We demonstrate on CIFAR-10, Fashion MNIST, and MNIST that our defense provides certified security against patch attacks of a certain size.
Forward citations
Cited by 1 Pith paper
-
Symbolic Knowledge Extraction and Injection with Sub-symbolic Predictors: A Systematic Literature Review
A systematic literature review of 132 symbolic knowledge extraction and 117 symbolic knowledge injection methods, with taxonomies and a survey of available software.
Discussion (0). Continue with ORCID to comment.