mlsanityData to 14 Oct 2026

Enhancing Adversarial Example Detection Through Model Explanation

arXiv 2503.09735 ↗First posted 12 Mar 2025cs.CR cs.CV cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

Adversarial examples are a major problem for machine learning models, leading to a continuous search for effective defenses. One promising direction is to leverage model explanations to better understand and defend against these attacks. We looked at AmI, a method proposed by a NeurIPS 2018 spotlight paper that uses model explanations to detect adversarial examples. Our study shows that while AmI is a promising idea, its performance is too dependent on specific settings (e.g., hyperparameter) and external factors such as the operating system and the deep learning framework used, and such drawbacks limit AmI's practical usage. Our findings highlight the need for more robust defense mechanisms that are effective under various conditions. In addition, we advocate for a comprehensive evaluation framework for defense techniques.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 27 of its 31 references that are in the map. First posted on arXiv 12 Mar 2025.

Builds on

27 of 31 references.

References · 27

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017A Unified Approach to Interpreting Model Predictionscited by 6,555
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  4. 2013Intriguing properties of neural networkscited by 5,155
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  6. 2016Adversarial examples in the physical worldcited by 1,769
  7. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  8. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,318
  9. 2016Adversarial Machine Learning at Scalecited by 936
  10. 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
  11. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  12. 2017Adversarial Patchcited by 517
15 more
  1. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  2. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  3. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  4. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 446
  5. 2018Defense-GAN: Protecting Classifiers Against Adversarial Attacks Using Generative Modelscited by 362
  6. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 269
  7. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 244
  8. 2016Improving the Robustness of Deep Neural Networks via Stability Trainingcited by 156
  9. 2017Adversarial examples for generative modelscited by 58
  10. 2019ML-LOO: Detecting Adversarial Examples with Feature Attributioncited by 48
  11. 2019When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signaturescited by 40
  12. 2018Attacks Meet Interpretability: Attribute-steered Detection of Adversarial Samplescited by 38
  13. 2019Attribution-driven Causal Analysis for Detection of Adversarial Examplescited by 8
  14. 2019Is AmI (Attacks Meet Interpretability) Robust to Adversarial Examples?cited by 7
  15. 2023Interpretability is a Kind of Safety: An Interpreter-based Ensemble for Adversary Defensecited by 6

Built on by

Not cited yet.