English

Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization

Human-Computer Interaction 2024-10-08 v2 Computer Vision and Pattern Recognition

Abstract

Adversarial machine learning (AML) studies attacks that can fool machine learning algorithms into generating incorrect outcomes as well as the defenses against worst-case attacks to strengthen model robustness. Specifically for image classification, it is challenging to understand adversarial attacks due to their use of subtle perturbations that are not human-interpretable, as well as the variability of attack impacts influenced by diverse methodologies, instance differences, and model architectures. Through a design study with AML learners and teachers, we introduce AdvEx, a multi-level interactive visualization system that comprehensively presents the properties and impacts of evasion attacks on different image classifiers for novice AML learners. We quantitatively and qualitatively assessed AdvEx in a two-part evaluation including user studies and expert interviews. Our results show that AdvEx is not only highly effective as a visualization tool for understanding AML mechanisms, but also provides an engaging and enjoyable learning experience, thus demonstrating its overall benefits for AML learners.

Keywords

Cite

@article{arxiv.2311.13656,
  title  = {Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization},
  author = {Yuzhe You and Jarvis Tse and Jian Zhao},
  journal= {arXiv preprint arXiv:2311.13656},
  year   = {2024}
}
R2 v1 2026-06-28T13:28:58.680Z