CosPGD: An Efficient White-Box Adversarial Attack for Pixel-Wise Prediction 
Tasks

Agnihotri, Shashank; Jung, Steffen; Keuper, Margret

Local TagsRelease HistoryDetailsSummary

CosPGD: An Efficient White-Box Adversarial Attack for Pixel-Wise Prediction Tasks

Agnihotri, S., Jung, S., & Keuper, M. (in press). CosPGD: An Efficient White-Box Adversarial Attack for Pixel-Wise Prediction Tasks. In Proceedings of the 41st International Conference on Machine Learning (pp. 26495-26516).

Item is Released

show all hide all

Basic

show hide

Item Permalink: https://hdl.handle.net/21.11116/0000-000F-3F1E-B Version Permalink: https://hdl.handle.net/21.11116/0000-000F-3F1F-A

Genre: Conference Paper

Latex : {CosPGD}: {A}n Efficient White-Box Adversarial Attack for Pixel-Wise Prediction Tasks

Files

show Files

Locators

show

Creators

show

hide

Creators:
Agnihotri, Shashank¹, Author
Jung, Steffen², Author
Keuper, Margret², Author

Affiliations:
1External Organizations, ou_persistent22
2Computer Vision and Machine Learning, MPI for Informatics, Max Planck Society, ou_1116547

Content

show

Details

show

hide

Language(s): eng - English

Dates: Accepted: 2024

Publication Status: Accepted / In Press

Pages: -

Publishing info: -

Table of Contents: -

Rev. Type: -

Identifiers: BibTex Citekey: Agnihotri_ICML24

Degree: -

Event

show

hide

Title: 41at International Conference on Machine Learning

Place of Event: Vienna, Austria

Start-/End Date: 2024-07-21 - 2024-07-27

Legal Case

show

Project information

show

Source 1

show

hide

Title: Proceedings of the 41st International Conference on Machine Learning

Abbreviation : ICML 2024

Source Genre: Proceedings

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 26495 - 26516 Identifier: -

Source 2

show

hide

Title: Proceedings of the Machine Learning Research

Abbreviation : PMLR

Source Genre: Series

Creator(s):

Affiliations:

Publ. Info: -

Pages: - Volume / Issue: - Sequence Number: - Start / End Page: - Identifier: ISSN: 1938-7228