mlsanityData to 7 Oct 2026

A simple defense against adversarial attacks on heatmap explanations

arXiv 2007.06381 ↗First posted 13 Jul 2020cs.LG cs.AI stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

With machine learning models being used for more sensitive applications, we rely on interpretability methods to prove that no discriminating attributes were used for classification. A potential concern is the so-called "fair-washing" - manipulating a model such that the features used in reality are hidden and more innocuous features are shown to be important instead. In our work we present an effective defence against such adversarial attacks on neural networks. By a simple aggregation of multiple explanation methods, the network becomes robust against manipulation. This holds even when the attacker has exact knowledge of the model weights and the explanation methods used.

Key facts. Cited by 23 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Jul 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 6; 2022: 7; 2023: 2; 2024: 8.

23 papers.

Sort:

By area:

  1. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  2. 2021Perturbing Inputs for Fragile Interpretations in Deep Natural Language Processingcited by 30
  3. 2021NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weightscited by 28
  4. 2022Robust Explanation Constraints for Neural Networkscited by 23
  5. 2022What Makes a Good Explanation?: A Harmonized View of Properties of Explanationscited by 21
  6. 2021Fooling Partial Dependence via Data Poisoningcited by 16
  7. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
  8. 2022Analyzing Explainer Robustness via Probabilistic Lipschitzness of Prediction Functionscited by 6
  9. 2021Improving Attribution Methods by Learning Submodular Functionscited by 5
  10. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  11. 2024When Can You Trust Your Explanations? A Robustness Analysis on Feature Importancescited by 5
  12. 2022Towards More Robust Interpretation via Local Gradient Alignmentcited by 4
11 more
  1. 2024Deciphering the Definition of Adversarial Robustness for post-hoc OOD Detectorscited by 2
  2. 2024Axiomatic Explainer Globalness via Optimal Transportcited by 2
  3. 2021Resilience of Bayesian Layer-Wise Explanations under Adversarial Attackscited by 1
  4. 2022Fidelity of Ensemble Aggregation for Saliency Map Explanations using Bayesian Optimization Techniquescited by 1
  5. 2022Provable Robust Saliency-based Explanationscited by 1
  6. 2024CNN-based explanation ensembling for dataset, representation and explanations evaluationcited by 1
  7. 2023Robust Ranking Explanationscited by 0
  8. 2024NormEnsembleXAI: Unveiling the Strengths and Weaknesses of XAI Ensemble Techniquescited by 0
  9. 2024Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoorscited by 0
  10. 2024The Anatomy of Adversarial Attacks: Concept-based XAI Dissectioncited by 0
  11. 2024Impact of Adversarial Attacks on Deep Learning Model Explainabilitycited by 0