Object-fabrication Targeted Attack for Object Detection

12/13/2022
by   Xuchong Zhang, et al.
0

Recent researches show that the deep learning based object detection is vulnerable to adversarial examples. Generally, the adversarial attack for object detection contains targeted attack and untargeted attack. According to our detailed investigations, the research on the former is relatively fewer than the latter and all the existing methods for the targeted attack follow the same mode, i.e., the object-mislabeling mode that misleads detectors to mislabel the detected object as a specific wrong label. However, this mode has limited attack success rate, universal and generalization performances. In this paper, we propose a new object-fabrication targeted attack mode which can mislead detectors to `fabricate' extra false objects with specific target labels. Furthermore, we design a dual attention based targeted feature space attack method to implement the proposed targeted attack mode. The attack performances of the proposed mode and method are evaluated on MS COCO and BDD100K datasets using FasterRCNN and YOLOv5. Evaluation results demonstrate that, the proposed object-fabrication targeted attack mode and the corresponding targeted feature space attack method show significant improvements in terms of image-specific attack, universal performance and generalization capability, compared with the previous targeted attack for object detection. Code will be made available.

READ FULL TEXT

page 1

page 3

page 5

page 6

page 7

page 8

page 9

research
12/19/2019

A New Ensemble Method for Concessively Targeted Multi-model Attack

It is well known that deep learning models are vulnerable to adversarial...
research
06/05/2020

Pick-Object-Attack: Type-Specific Adversarial Attack for Object Detection

Many recent studies have shown that deep neural models are vulnerable to...
research
08/29/2019

Universal, transferable and targeted adversarial attacks

Deep Neural Network has been found vulnerable in many previous works. A ...
research
11/16/2022

Attacking Object Detector Using A Universal Targeted Label-Switch Patch

Adversarial attacks against deep learning-based object detectors (ODs) h...
research
02/19/2015

Visualizing Object Detection Features

We introduce algorithms to visualize feature spaces used by object detec...
research
04/29/2020

Perturbing Across the Feature Hierarchy to Improve Standard and Strict Blackbox Attack Transferability

We consider the blackbox transfer-based targeted adversarial attack thre...
research
12/11/2012

Inverting and Visualizing Features for Object Detection

We introduce algorithms to visualize feature spaces used by object detec...

Please sign up or login with your details

Forgot password? Click here to reset