Metraipolis › archive › dc_7ebe26930cbb

ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models — arXiv:2608.21803

Source: arXiv (en)
Original: https://arxiv.org/abs/2608.21803
License (as archived): CC0-1.0
Archived: 2026-10-18T07:42:25.422Z
SHA-256 of the archived text: 1e4bbb8d69d94940240d01c2b5676221faa65475ab129fbd432e7d25e8bb22af
Stable URL of this page: https://metraipolis.com/documento/dc_7ebe26930cbb

How to cite

ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models — arXiv:2608.21803 — arXiv (en), https://arxiv.org/abs/2608.21803 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7ebe26930cbb (Metraipolis archive dc_7ebe26930cbb, sha256 1e4bbb8d69d94940240d01c2b5676221faa65475ab129fbd432e7d25e8bb22af)

BibTeX

@misc{dc7ebe26930cbb,
  title = {ExplainGuard: A Zero Trust Framework for Post-Hoc Explanation Integrity Guarantees in Blackbox XAI Models — arXiv:2608.21803},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.21803},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7ebe26930cbb; sha256 1e4bbb8d69d94940240d01c2b5676221faa65475ab129fbd432e7d25e8bb22af},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.21803. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As machine learning (ML) models are increasingly deployed in high-stakes environments, explainable AI (XAI) methods like SHAP and LIME have become essential for regulatory compliance and trust. However, the current auditing paradigm relies on an implicit "chain of trust" where third-party auditors are assumed to be trusted. Recent research demonstrates that this assumption is flawed and adversarial auditors can manipulate XAI explanations through manipulation attacks such as output shuffling or scaffolding out-of-distribution (OOD) to conceal model biases while maintaining high prediction accuracy aiming for fairwashed explanation. In this paper, we introduce a novel defense framework, ExplainGuard, that leverages a Zero-Trust architecture (ZTA) design to be incorporated within the XAI explanation supply chain and ensures the integrity of the generated explanation. This framework would help us to replace the ambiguous default assumption of "auditor is trustworthy," with a continuous "verify-then-trust" approach. Our design architecture establishes a Policy Decision Point (PDP) that enforces three distinct pillars of verification before any explanation is released to the user: (1) asset integrity via behavioral fingerprint to detect model substitution, (2) semantic validity using axiomatic consistency checks to reject mathematically impossible explanations, and (3) feature faithfulness verification utilizing a ranking stability approach with minimal computational overhead. Finally, we evaluate how ExplainGuard can effectively neutralize state- of-the-art explanation manipulation attacks while transforming the auditing process into a verifiable operation.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-25 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2608.21803 — 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 2026-10-18T07:37:52.832Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-25?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).