Adversarial Attacks against Blind Image Quality Assessment Models

Jari Korhonen, Junyong You

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

2 Citations (Scopus)

Abstract

Several deep models for blind image quality assessment (BIQA) have been proposed during the past few years, with promising results on standard image quality datasets. However, generalization of BIQA models beyond the standard content remains a challenge. In this paper, we study basic adversarial attack techniques to assess the robustness of representative deep BIQA models. Our results show that adversarial images created for a simple substitute BIQA model (i.e. white-box scenario) are transferable as such and able to deceive also several other more complex BIQA models (i.e. black-box scenario). We also investigated some basic defense mechanisms. Our results indicate that re-training BIQA models with a dataset augmented with adversarial images improves robustness of several models, but at the cost of decreased quality prediction accuracy on genuine images.
Original languageEnglish
Title of host publicationQoEVMA '22
Subtitle of host publicationProceedings of the 2nd Workshop on Quality of Experience in Visual Multimedia Applications
PublisherAssociation for Computing Machinery
Number of pages9
ISBN (Electronic)978-1-4503-9499-4
DOIs
Publication statusPublished - 14 Oct 2022
Event2nd Workshop on Quality of Experience in Visual Multimedia Applications (QoEVMA) at ACM Multimedia - Lisbon, Portugal
Duration: 10 Oct 202214 Oct 2022
https://2022.acmmm.org/

Publication series

NameQoEVMA 2022 - Proceedings of the 2nd Workshop on Quality of Experience in Visual Multimedia Applications

Conference

Conference2nd Workshop on Quality of Experience in Visual Multimedia Applications (QoEVMA) at ACM Multimedia
Country/TerritoryPortugal
CityLisbon
Period10/10/2214/10/22
Internet address

Bibliographical note

Funding Information:
This work was supported in part by Natural Science Foundation of China under grant 61772348, Guangdong ”Pearl River Talent Recruitment Program” under Grant 2019ZT08X603, and Shenzhen Technology R&D Fund under Grant 202008121558110.

Keywords

  • Image quality assessment
  • Quality of Experience
  • Adversarial attacks
  • Adversarial defenses

Fingerprint

Dive into the research topics of 'Adversarial Attacks against Blind Image Quality Assessment Models'. Together they form a unique fingerprint.

Cite this