AIR-ML
Home
Research
News
Team
Project
Publication
Position
Contact
Adversarial Patch
IAP: Invisible Adversarial Patch Attack through Perceptibility-Aware Localization and Perturbation Optimization
We develop a novel attack framework that generates highly invisible adversarial patches based on perceptibility-aware localization and perturbation schemes.
Subrat Kishore Dutta
,
Xiao Zhang
PDF
Cite
Code
ArXiv
DiffPAD: Denoising Diffusion-based Adversarial Patch Decontamination
We propose DiffPAD, a novel framework that harnesses the power of diffusion models for adversarial patch decontamination.
Jia Fu
,
Xiao Zhang
,
Sepideh Pashami
,
Fatemeh Rahimian
,
Anders Holst
PDF
Cite
ArXiv
Cite
×