mlsanityData to 14 Oct 2026

Panda or not Panda? Understanding Adversarial Attacks with Interactive Visualization

arXiv 2311.13656 ↗First posted 22 Nov 2023cs.HC cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 35 of its 66 references that are in the map. First posted on arXiv 22 Nov 2023.

Builds on

35 of 66 references.

References · 35

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2016PointNet: Deep Learning on Point Sets for 3D Classification and Segmentationcited by 5,248
  4. 2014Going Deeper with Convolutionscited by 4,241
  5. 2016Adversarial examples in the physical worldcited by 1,769
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  9. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  10. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  11. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  12. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 661
23 more
  1. 2017One pixel attack for fooling deep neural networkscited by 582
  2. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 514
  3. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 333
  4. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  5. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 274
  6. 2019Fooling automated surveillance cameras: adversarial patches to attack person detectioncited by 268
  7. 2020Understanding and Mitigating the Tradeoff Between Robustness and Accuracycited by 149
  8. 2019Adversarial Robustness through Local Linearizationcited by 146
  9. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  10. 2018Parametric Noise Injection: Trainable Randomness to Improve Deep Neural Network Robustness against Adversarial Attackcited by 125
  11. 2019A Survey of Deep Learning Applications to Autonomous Vehicle Controlcited by 106
  12. 2019Summit: Scaling Deep Learning Interpretability by Visualizing Activation and Attribution Summarizationscited by 72
  13. 2020CNN Explainer: Learning Convolutional Neural Networks with Interactive Visualizationcited by 57
  14. 2017ActiVis: Visual Exploration of Industry-Scale Deep Neural Network Modelscited by 56
  15. 2017Efficient Defenses Against Adversarial Attackscited by 53
  16. 2020Robustness May Be at Odds with Fairness: An Empirical Study on Class-wise Accuracycited by 45
  17. 2016Early Methods for Detecting Adversarial Imagescited by 36
  18. 2020Analyzing the Noise Robustness of Deep Neural Networkscited by 31
  19. 2019Explaining Vulnerabilities to Adversarial Machine Learning through Visual Analyticscited by 24
  20. 2021Untargeted, Targeted and Universal Adversarial Attacks and Defenses on Time Seriescited by 21
  21. 2020Defense-PointNet: Protecting PointNet Against Adversarial Attackscited by 13
  22. 2020Bluff: Interactively Deciphering Adversarial Attacks on Deep Neural Networkscited by 12
  23. 2017Adversarial-Playground: A Visualization Suite Showing How Adversarial Examples Fool Deep Learningcited by 8

Built on by

Cited by year

Citing papers per year: 2024: 1; 2025: 1.

2 papers.

  1. 2024Transformer Explainer: Learning LLM Transformers with Interactive Visual Explanation and Experimentationcited by 10
  2. 2025NeuroBreak: Unveil Internal Jailbreak Mechanisms in Large Language Modelscited by 1