Detection of sticker based adversarial attacks

András Horváth; Csanád Egervári

doi:10.1117/12.2503219

9 August 2018 Detection of sticker based adversarial attacks

András Horváth, Csanád Egervári

Proceedings Volume 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018); 108066Y (2018) https://doi.org/10.1117/12.2503219
Event: Tenth International Conference on Digital Image Processing (ICDIP 2018), 2018, Shanghai, China

Abstract

Adversarial examples revealed and important aspect of convolutional neural networks and are getting more and more attention in machine learning. It was shown that not only small perturbations, covering the whole image can be applied but also sticker based attacks, concentrated on small regions of the image can cause misclassification. Meanwhile the first type of attack is theoretical the later can be applied in practice and lead tomisclassification in image processing pipelines. In this paper we show a method how sticker based adversarial samples can be detected by calculating the responses of the neurons in the last layers and estimating the measure of region based classification consistency.

Citation Download Citation

András Horváth and Csanád Egervári "Detection of sticker based adversarial attacks", Proc. SPIE 10806, Tenth International Conference on Digital Image Processing (ICDIP 2018), 108066Y (9 August 2018); https://doi.org/10.1117/12.2503219

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
5 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image classification

Neural networks

Convolutional neural networks

Image processing

Machine learning

RELATED CONTENT

An image classification method based on few-shot learning
Proceedings of SPIE (August 01 2023)

Influence of images generated by CGAN on the performance of...
Proceedings of SPIE (March 28 2023)

Modern approaches in deep learning for SAR ATR
Proceedings of SPIE (May 14 2016)

Weakly supervised pancreas segmentation based on class activation maps
Proceedings of SPIE (March 10 2020)

Left ventricle segmentation in cardiac MRI images using fully convolutional...
Proceedings of SPIE (March 03 2017)

A survey of the application of deep learning in computer...
Proceedings of SPIE (August 31 2018)

Research on image recognition system based on artificial intelligence
Proceedings of SPIE (August 10 2023)

Subscribe to Digital Library

Receive Erratum Email Alert

Keywords/Phrases

Search In:

Publication Years