Adversarial attacks and defenses in explainable artificial intelligence: A survey

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Baniecki, Hubert, Biecek, Przemyslaw
Format: Preprint
Published: 2023
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912506010664960
author Baniecki, Hubert
Biecek, Przemyslaw
author_facet Baniecki, Hubert
Biecek, Przemyslaw
contents Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging and trusting statistical and deep learning models, as well as interpreting their predictions. However, recent advances in adversarial machine learning (AdvML) highlight the limitations and vulnerabilities of state-of-the-art explanation methods, putting their security and trustworthiness into question. The possibility of manipulating, fooling or fairwashing evidence of the model's reasoning has detrimental consequences when applied in high-stakes decision-making and knowledge discovery. This survey provides a comprehensive overview of research concerning adversarial attacks on explanations of machine learning models, as well as fairness metrics. We introduce a unified notation and taxonomy of methods facilitating a common ground for researchers and practitioners from the intersecting research fields of AdvML and XAI. We discuss how to defend against attacks and design robust interpretation methods. We contribute a list of existing insecurities in XAI and outline the emerging research directions in adversarial XAI (AdvXAI). Future work should address improving explanation methods and evaluation protocols to take into account the reported safety issues.
format Preprint
id arxiv_https___arxiv_org_abs_2306_06123
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Adversarial attacks and defenses in explainable artificial intelligence: A survey
Baniecki, Hubert
Biecek, Przemyslaw
Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
Explainable artificial intelligence (XAI) methods are portrayed as a remedy for debugging and trusting statistical and deep learning models, as well as interpreting their predictions. However, recent advances in adversarial machine learning (AdvML) highlight the limitations and vulnerabilities of state-of-the-art explanation methods, putting their security and trustworthiness into question. The possibility of manipulating, fooling or fairwashing evidence of the model's reasoning has detrimental consequences when applied in high-stakes decision-making and knowledge discovery. This survey provides a comprehensive overview of research concerning adversarial attacks on explanations of machine learning models, as well as fairness metrics. We introduce a unified notation and taxonomy of methods facilitating a common ground for researchers and practitioners from the intersecting research fields of AdvML and XAI. We discuss how to defend against attacks and design robust interpretation methods. We contribute a list of existing insecurities in XAI and outline the emerging research directions in adversarial XAI (AdvXAI). Future work should address improving explanation methods and evaluation protocols to take into account the reported safety issues.
title Adversarial attacks and defenses in explainable artificial intelligence: A survey
topic Cryptography and Security
Artificial Intelligence
Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2306.06123