Feasibility of Inconspicuous GAN-generated Adversarial Patches against Object Detection

by   Svetlana Pavlitskaya, et al.

Standard approaches for adversarial patch generation lead to noisy conspicuous patterns, which are easily recognizable by humans. Recent research has proposed several approaches to generate naturalistic patches using generative adversarial networks (GANs), yet only a few of them were evaluated on the object detection use case. Moreover, the state of the art mostly focuses on suppressing a single large bounding box in input by overlapping it with the patch directly. Suppressing objects near the patch is a different, more complex task. In this work, we have evaluated the existing approaches to generate inconspicuous patches. We have adapted methods, originally developed for different computer vision tasks, to the object detection use case with YOLOv3 and the COCO dataset. We have evaluated two approaches to generate naturalistic patches: by incorporating patch generation into the GAN training process and by using the pretrained GAN. For both cases, we have assessed a trade-off between performance and naturalistic patch appearance. Our experiments have shown, that using a pre-trained GAN helps to gain realistic-looking patches while preserving the performance similar to conventional adversarial patches.


page 1

page 2

page 4

page 5

page 6

page 7

page 8


AdvART: Adversarial Art for Camouflaged Object Detection Attacks

A majority of existing physical attacks in the real world result in cons...

It GAN DO Better: GAN-based Detection of Objects on Images with Varying Quality

In this paper, we propose in our novel generative framework the use of G...

Vax-a-Net: Training-time Defence Against Adversarial Patch Attacks

We present Vax-a-Net; a technique for immunizing convolutional neural ne...

Jedi: Entropy-based Localization and Removal of Adversarial Patches

Real-world adversarial physical patches were shown to be successful in c...

Diffusion to Confusion: Naturalistic Adversarial Patch Generation Based on Diffusion Model for Object Detector

Many physical adversarial patch generation methods are widely proposed t...

COCO-GAN: Generation by Parts via Conditional Coordinating

Humans can only interact with part of the surrounding environment due to...

Raw Bayer Pattern Image Synthesis with Conditional GAN

In this paper, we propose a method to generate Bayer pattern images by G...

Please sign up or login with your details

Forgot password? Click here to reset