On the generation of adversarial examples for image quality assessment

Qingbing Sang*, Hongguo Zhang, Lixiong Liu, Xiaojun Wu, Alan C. Bovik

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

3 Citations (Scopus)

Abstract

We study the generation of adversarial examples to test, assess, and improve deep learning-based image quality assessment (IQA) algorithms. This is important since social media platforms and other providers rely on IQA models to monitor the content they ingest, and to control the quality of pictures that are shared. Unfortunately, IQA models based on deep learning are vulnerable to adversarial attacks. Combining the characteristics of IQA, we analyze several methods of generating adversarial examples in the classification field, and generate adversarial image quality assessment examples by obtaining model gradient information, image pixel information and reconstruction loss function. And we create an adversarial examples image generation tool that generates aggressive adversarial examples having good attack success rates. We hope that it can be used to help IQA researchers assess and improve the robustness of IQA.

Original languageEnglish
Pages (from-to)3183-3198
Number of pages16
JournalVisual Computer
Volume40
Issue number5
DOIs
Publication statusPublished - May 2024

Keywords

  • Adversarial example
  • Deep learning
  • Image quality assessment

Fingerprint

Dive into the research topics of 'On the generation of adversarial examples for image quality assessment'. Together they form a unique fingerprint.

Cite this