Enregistré dans:
Détails bibliographiques
Auteur principal: Burger, Christopher
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:https://arxiv.org/abs/2501.01516
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866912792284495872
author Burger, Christopher
author_facet Burger, Christopher
contents Adversarial attacks challenge the reliability of Explainable AI (XAI) by altering explanations while the model's output remains unchanged. The success of these attacks on text-based XAI is often judged using standard information retrieval metrics. We argue these measures are poorly suited in the evaluation of trustworthiness, as they treat all word perturbations equally while ignoring synonymity, which can misrepresent an attack's true impact. To address this, we apply synonymity weighting, a method that amends these measures by incorporating the semantic similarity of perturbed words. This produces more accurate vulnerability assessments and provides an important tool for assessing the robustness of AI systems. Our approach prevents the overestimation of attack success, leading to a more faithful understanding of an XAI system's true resilience against adversarial manipulation.
format Preprint
id arxiv_https___arxiv_org_abs_2501_01516
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Quantifying True Robustness: Synonymity-Weighted Similarity for Trustworthy XAI Evaluation
Burger, Christopher
Machine Learning
Artificial Intelligence
Computation and Language
Adversarial attacks challenge the reliability of Explainable AI (XAI) by altering explanations while the model's output remains unchanged. The success of these attacks on text-based XAI is often judged using standard information retrieval metrics. We argue these measures are poorly suited in the evaluation of trustworthiness, as they treat all word perturbations equally while ignoring synonymity, which can misrepresent an attack's true impact. To address this, we apply synonymity weighting, a method that amends these measures by incorporating the semantic similarity of perturbed words. This produces more accurate vulnerability assessments and provides an important tool for assessing the robustness of AI systems. Our approach prevents the overestimation of attack success, leading to a more faithful understanding of an XAI system's true resilience against adversarial manipulation.
title Quantifying True Robustness: Synonymity-Weighted Similarity for Trustworthy XAI Evaluation
topic Machine Learning
Artificial Intelligence
Computation and Language
url https://arxiv.org/abs/2501.01516