Pith. sign in

REVIEW 1 cited by

UPSET and ANGRI : Breaking High Performance Image Classifiers

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

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

arxiv 1707.01159 v1 pith:5ZOLCSTE submitted 2017-07-04 cs.CV

Sayantan Sarkar , Ankan Bansal , Upal Mahbub , Rama Chellappa This is my paper · ORCID
classification cs.CV
keywords imageclassifiersgenerateshighperformanceperturbationsachievedalgorithms
verification ladder T0 review T1 audit T2 compute T3 formal

Signed reviews

No signed human review yet.

0 comments
read the original abstract

In this paper, targeted fooling of high performance image classifiers is achieved by developing two novel attack methods. The first method generates universal perturbations for target classes and the second generates image specific perturbations. Extensive experiments are conducted on MNIST and CIFAR10 datasets to provide insights about the proposed algorithms and show their effectiveness.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. On the Robustness of Human Pose Estimation

    cs.CV 2019-08 conditional novelty 6.0 of 10

    Human pose estimation models are relatively robust to single-step attacks, but heatmap-based and structure-aware models resist attacks better than direct-regression models, and universal perturbations can still break them.

Pith tools