Robustness evaluation of object detection models: a gradient attack method based on spatial sensitivity

Kai Fu; Mingzheng Wang; Kuangyin Meng; Changbin Shao

doi:10.1117/12.2685460

15 August 2023 Robustness evaluation of object detection models: a gradient attack method based on spatial sensitivity

Kai Fu, Mingzheng Wang, Kuangyin Meng, Changbin Shao

Proceedings Volume 12719, Second International Conference on Electronic Information Technology (EIT 2023); 1271936 (2023) https://doi.org/10.1117/12.2685460
Event: Second International Conference on Electronic Information Technology (EIT 2023), 2023, Wuhan, China

Abstract

In the field of model robustness, adversarial attacks have become the most powerful way to threaten the performance of various deep models; adversarial attacks are to add adversarial noise to common samples to generate adversarial samples in order to mislead the model. The aggressiveness and imperceptibility of its noise are two main indicators to measure the adversarial attack. In this paper, we focus on attacks on object detection models. Previous gradient-sign based noise generation methods have achieved powerful attacks, however the adversarial examples they generate are usually easily perceived by our visual system. This is mainly due to the crude sign noise addition strategy adopted by the gradient sign method on the global input space. To solve this problem, the sensitivity of the deep detection model to the input sample space is analyzed, and a gradient attack method based on space sensitivity is proposed based on this clue. Specifically, inspired by the attention mechanism of the deep model, we investigate the global gradient information of the entire image, and verify the spatial regions that play a key role in detection and classification; further, we propose a method based on the key gradient information noise screening strategy to generate adversarial examples. This not only avoids the perceptibility flaw caused by directly attaching the global gradient symbol, but also provides a more powerful attack effect. Taking the Yolov3 detection model as an example, we conducted observational verification and offensive testing on the VOC detection dataset, and the experimental results confirmed the effectiveness of our method. This poses a greater challenge on how to conduct more effective model defense.

Citation Download Citation

Kai Fu, Mingzheng Wang, Kuangyin Meng, and Changbin Shao "Robustness evaluation of object detection models: a gradient attack method based on spatial sensitivity", Proc. SPIE 12719, Second International Conference on Electronic Information Technology (EIT 2023), 1271936 (15 August 2023); https://doi.org/10.1117/12.2685460

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
6 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Object detection

Performance modeling

Data modeling

Statistical modeling

Defense and security

Detection and tracking algorithms

Image classification

Show All Keywords

Keywords/Phrases

Search In:

Publication Years