Toggle navigation
OpenReview
.net
Login
×
Go to
DBLP
homepage
Attentional Feature Erase: Towards task-wise transferable adversarial attack on cloud vision APIs
Bo Cheng
,
Yantao Lu
,
Yilan Li
,
Tao You
,
Peng Zhang
Published: 01 Jan 2024, Last Modified: 14 Nov 2024
Displays 2024
Everyone
Revisions
BibTeX
CC BY-SA 4.0
Abstract:
Highlights•Proposed adversarial examples effectively transfer across vision tasks and networks.•Reducing dispersion in intermediate features lessens robustness.•Gradient aggregation highlights key regions in the network.
Loading