JSAI2024

Presentation information

General Session

General Session » GS-11 AI and Society

[2G1-GS-11] AI and Society:

Wed. May 29, 2024 9:00 AM - 10:40 AM Room G (Room 22+23)

座長:髙橋 翼(LINEヤフー/SB Intuitions)

10:20 AM - 10:40 AM

[2G1-GS-11-05] Detection of adversarial examples based on similarity between object external features described in natural language and images

〇Yuto Yoshinari1, Zhe Yu2, Kazuto Fukuchi3, Jun Sakuma1,2 (1. Tokyo University of Engineering, 2. RIKEN, 3. University of Tsukuba)

Keywords:AI Security, Adversarial Example

Detection of adversarial examples is an important issue. This research focuses on the fact that the adversarial example looks similar to the original image and the appearance features of the object. Through experiments on Cifar-10 and Tiny-ImageNet, we have shown that the proposed method achieves a certain detection performance in the black box setting, and we confirmed that Tiny-ImageNet performs better when using object appearance features to detect hostile samples.We also confirmed that the performance of the no-box setting is not so different from that of the black-box setting.

Authentication for paper PDF access

A password is required to view paper PDFs. If you are a registered participant, please log on the site from Participant Log In.
You could view the PDF with entering the PDF viewing password bellow.

Password