PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning

doi:doi:10.57702/5ue6lm5a

PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning

Patch-based attacks introduce a perceptible but localized change to the input that induces misclassiﬁcation. A limitation of cur- rent patch-based black-box attacks is that they perform poorly for tar- geted attacks, and even for the less challenging non-targeted scenarios, they require a large number of queries.

Data and Resources

Original MetadataJSON
The json representation of the dataset with its distributions based on DCAT.
Explore
- Preview
- Download

Cite this as

Chenglin Yang, Adam Kortylewski, Cihang Xie, Yinzhi Cao, Alan Yuille (2024). Dataset: PatchAttack: A Black-box Texture-based Attack with Reinforcement Learning. https://doi.org/10.57702/5ue6lm5a

DOI retrieved: December 2, 2024

Additional Info

Field	Value
Created	December 2, 2024
Last update	December 2, 2024
Author	Chenglin Yang
More Authors	Adam Kortylewski Cihang Xie Yinzhi Cao Alan Yuille
Homepage	https://arxiv.org/abs/2006.10923