Adversarial Attacks in Explainable Machine Learning: A Survey of Threats Against Models and Humans
WIREs Data Mining and Knowledge Discovery · 2025-03 · 15 (1)
DOI: 10.1002/widm.1567 ↗At a glance
Journal article in WIREs Data Mining and Knowledge Discovery, published online on 2024-10-27. Written by Jon Vadillo and 2 co-authors. Cited 34 times so far (Crossref); 201 references. The full text is freely available (open access, CC BY 4.0). Funded by: Eusko Jaurlaritza, Ministerio de Economía y Competitividad.
Abstract (original language)
Reliable deployment of machine learning models such as neural networks continues to be challenging due to several limitations. Some of the main shortcomings are the lack of interpretability and the lack of robustness against adversarial examples or out‐of‐distribution inputs. In this paper, we comprehensively review the possibilities and limits of adversarial attacks for explainable machine learning models. First, we extend the notion of adversarial examples to fit in explainable machine learning scenarios where a human assesses not only the input and the output classification, but also the explanation of the model's decision. Next, we propose a comprehensive framework to study whether (and how) adversarial examples can be generated for explainable models under human assessment. Based on this framework, we provide a structured review of the diverse attack paradigms existing in this domain, identify current gaps and future research directions, and illustrate the main attack paradigms discussed. Furthermore, our framework considers a wide range of relevant yet often ignored factors such as the type of problem, the user expertise or the objective of the explanations, in order to identify the attack strategies that should be adopted in each scenario to successfully deceive the model (and the human). The intention of these contributions is to serve as a basis for a more rigorous and realistic study of adversarial examples in the field of explainable machine learning.
Funding
- Eusko Jaurlaritza
- Ministerio de Economía y Competitividad
Cite
APA
Vadillo, J., Santana, R., & Lozano, J. A. (2025). Adversarial Attacks in Explainable Machine Learning: A Survey of Threats Against Models and Humans. WIREs Data Mining and Knowledge Discovery, 15(1). https://doi.org/10.1002/widm.1567
Vancouver
Vadillo J, Santana R, Lozano JA. Adversarial Attacks in Explainable Machine Learning: A Survey of Threats Against Models and Humans. WIREs Data Mining and Knowledge Discovery. 2025;15(1). doi:10.1002/widm.1567
BibTeX
@article{Vadillo2025,
author = {Vadillo, Jon and Santana, Roberto and Lozano, Jose A.},
title = {Adversarial Attacks in Explainable Machine Learning: A Survey of Threats Against Models and Humans},
journal = {WIREs Data Mining and Knowledge Discovery},
year = {2025},
volume = {15},
number = {1},
doi = {10.1002/widm.1567}
}
EUVIMED