Metraipolis › archive › dc_3db29bcb70df

A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification — arXiv:2608.23817

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.23817
License (as archived): CC0-1.0
Archived: 2026-10-18T06:36:35.800Z
SHA-256 of the archived text: 071a661304fc65758393bb9b326341d10257cc8c642aee7d8900f666319bec2d
Stable URL of this page: https://metraipolis.com/documento/dc_3db29bcb70df

How to cite

A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification — arXiv:2608.23817 — arXiv (en), https://arxiv.org/abs/2608.23817 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_3db29bcb70df (Metraipolis archive dc_3db29bcb70df, sha256 071a661304fc65758393bb9b326341d10257cc8c642aee7d8900f666319bec2d)

BibTeX

@misc{dc3db29bcb70df,
  title = {A Formal Methodological Framework for Auditing Robustness and Fidelity in Explainable AI: From Application to Trust Certification — arXiv:2608.23817},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.23817},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_3db29bcb70df; sha256 071a661304fc65758393bb9b326341d10257cc8c642aee7d8900f666319bec2d},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.23817. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

SHAP and LIME are now standard tools for interpreting black-box predictions, yet their outputs can vary substantially when the input is perturbed by small amounts of noise--a problem we observed firsthand in our previous work on food security in Madagascar (Ralinirina et al., 2025). This variability raises the question of whether such explanations can be trusted at all. We address it by constructing an auditing protocol that measures two properties of any post-hoc explainer: robustness (how stable the explanation is under input perturbation) and fidelity (whether the features deemed important actually drive the model's prediction). These two quantities are combined into a single Trust Score. We run the protocol on a multi-sectoral dataset from Madagascar (83 features, 253 records, 4 malnutrition classes) using three classifiers and two explainers, plus their regularized counterparts. The results are sobering: models with AUC above 0.99 can produce numerically degenerate or flatly uninformative explanations, and fidelity scores lose discriminative power when the model is overfitted. These findings suggest that auditing XAI outputs is not optional but necessary, particularly when they inform decisions in sensitive domains.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-26 in cs.LG).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computers and Society (cs.CY); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2608.23817 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-18T06:28:52.315Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-08-26?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).