Bias-based Universal Adversarial Patch Attack for Automatic Check-out
Adversarial examples are inputs with imperceptible perturbations that easily misleading deep neural networks(DNNs). Recently, adversarial patch, with noise confined to a small and localized patch, has emerged for its easy feasibility in real-world scenarios. However, existing strategies failed to ge...
Saved in:
Main Authors | , , , , , |
---|---|
Format | Journal Article |
Language | English |
Published |
19.05.2020
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Summary: | Adversarial examples are inputs with imperceptible perturbations that easily
misleading deep neural networks(DNNs). Recently, adversarial patch, with noise
confined to a small and localized patch, has emerged for its easy feasibility
in real-world scenarios. However, existing strategies failed to generate
adversarial patches with strong generalization ability. In other words, the
adversarial patches were input-specific and failed to attack images from all
classes, especially unseen ones during training. To address the problem, this
paper proposes a bias-based framework to generate class-agnostic universal
adversarial patches with strong generalization ability, which exploits both the
perceptual and semantic bias of models. Regarding the perceptual bias, since
DNNs are strongly biased towards textures, we exploit the hard examples which
convey strong model uncertainties and extract a textural patch prior from them
by adopting the style similarities. The patch prior is more close to decision
boundaries and would promote attacks. To further alleviate the heavy dependency
on large amounts of data in training universal attacks, we further exploit the
semantic bias. As the class-wise preference, prototypes are introduced and
pursued by maximizing the multi-class margin to help universal training. Taking
AutomaticCheck-out (ACO) as the typical scenario, extensive experiments
including white-box and black-box settings in both digital-world(RPC, the
largest ACO related dataset) and physical-world scenario(Taobao and JD, the
world' s largest online shopping platforms) are conducted. Experimental results
demonstrate that our proposed framework outperforms state-of-the-art
adversarial patch attack methods. |
---|---|
DOI: | 10.48550/arxiv.2005.09257 |