Saved in:
Bibliographic Details
Main Author: Kim, Minyeong
Format: Recurso digital
Language:
Published: Zenodo 2026
Subjects:
Online Access:https://doi.org/10.5281/zenodo.19688326
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866901668286693376
author Kim, Minyeong
author_facet Kim, Minyeong
contents Analysis pipeline and statistical scripts supporting the factorial audit of five post-hoc attribution methods (Integrated Gradients, Grad-CAM, SmoothGrad, GradientSHAP, LIME) under fifteen common corruptions at five severity levels on CIFAR-10-C and CIFAR-100-C, across ResNet-50 and ViT-B/16 classifiers.
format Recurso digital
id zenodo_https___doi_org_10_5281_zenodo_19688326
institution Zenodo
language
publishDate 2026
publisher Zenodo
record_format zenodo
spellingShingle Systematic Vulnerability Audit of Post-Hoc XAI under Common Corruptions: Analysis Pipeline
Kim, Minyeong
Explainable Artificial Intelligence
Attribution Stability
Distribution Shift
Common Corruptions
Vision Transformer
Model-Agnostic Explanation
Analysis pipeline and statistical scripts supporting the factorial audit of five post-hoc attribution methods (Integrated Gradients, Grad-CAM, SmoothGrad, GradientSHAP, LIME) under fifteen common corruptions at five severity levels on CIFAR-10-C and CIFAR-100-C, across ResNet-50 and ViT-B/16 classifiers.
title Systematic Vulnerability Audit of Post-Hoc XAI under Common Corruptions: Analysis Pipeline
topic Explainable Artificial Intelligence
Attribution Stability
Distribution Shift
Common Corruptions
Vision Transformer
Model-Agnostic Explanation
url https://doi.org/10.5281/zenodo.19688326