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

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

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.

When Can We Trust Fairness Audits? Identifying Reliability Boundaries of Third-party Audit Conclusions

Beyond Local Accuracy: A Protocol-Level Identifiability Audit for Controlled LLM Reasoning Evaluation

LLM benchmark scores can be precise even when the observation protocol does not identify the behavioral property they are intended to measure. In a controlled, solver-grounded setting, we formalize a protocol-level identifiability audit over a finite behavioral policy class: given policies H, observation support O, and estimand $\tau$, we test whether O separates every pair with different $\tau$. The audit requires zero model calls and resolves our diagnostic case: base-only observation collapses seven frozen deterministic policies into one equivalence class; full support yields seven classes and no cross-estimand collisions; every leave-one-out support retains a constructive collision witness. Empirically, both constrained-generation variants have pair-validity 1.0, yet base accuracy and selective-response fidelity diverge - 0.620 versus 0.324 across six balanced oracle-transition directions (cluster-bootstrap 95% CI [0.600, 0.642] vs. [0.304, 0.345]) - and the gap recurs on a second deterministic source (0.646 vs. 0.331). The audit also synthesizes a minimum identifying support $O^*$ for the frozen policy class: two cells instead of the full 36-cell tensor. This case shows how evaluation-design validity can be checked structurally before model inference and why base correctness does not determine intervention-response fidelity.

From Black Box to Boardroom: The Significance of Explainable AI (XAI) in Reducing Algorithmic Risk and Rebuilding Confidence in Digital Payment Systems

The wide implementation of advanced Machine Learning (ML) models in digital payment systems, especially for fraud detection and credit risk assessment, has substantially improved operational efficiency and transaction security. The inherent opacity, often referred to as the black box character, of these high-performing algorithms poses considerable and mounting issues related to algorithmic fairness, stakeholder trust, and compliance with regulations. This article analyzes the growing strategic significance of Explainable Artificial Intelligence (XAI) as an important governance tool for mitigating algorithmic risk in financial services. The paper exposes how XAI, informed by Agency Theory and Institutional Theory, is not just a technical requirement but an essential institutional mechanism for ensuring regulatory accountability within frameworks like the EU AI Act, restoring public trust and identifying and alleviating systemic algorithmic bias in credit scoring and fraud risk assessment. A conceptual framework is introduced and it illustrates how XAI; using post-hoc interpretation methods such as SHAP (SHapley Additive exPlanations) and LIME (Local Interpretable Model-agnostic Explanations)- bridges the knowledge disparity between intricate AI models and various human stakeholders, including customers, fraud analysts, and regulators. This transformation shifts AI from a hypothetical institutional liability to a responsible, auditable, and governable asset within the digital payment ecosystem. The report concluded by describing key areas for forthcoming empirical research on the organizational problems associated with XAI implementation across various regulatory jurisdictions

Who Verifies the Benchmark? Decentralizing Trust in Large Language Model Evaluation

LLM benchmarks can build an organization's reputation and attract customers, but only when results are transparent and verifiable. Unverified claims that DeepSeek R1 outperformed OpenAI's o1 contributed to market panic on January 27, 2025, when Nvidia lost USD589 billion in market value. Yet vendor benchmarks often depend on an honor system. Academic reassessments and independent leaderboards have found undisclosed changes to proprietary models, contaminated training data, and selective reporting. LLM-as-a-judge methods scale evaluation by reducing human review. Studies, however, suggest that judges may show identity-aware bias, scoring an answer according to its source model rather than its quality. This bias has not been fully measured or corrected across politically sensitive, reasoning-intensive, and preference-based tasks. We examine this problem using seven verifier models: GPT-OSS 120B, Llama 3.3 70B, GLM 5.1, Qwen3 32B, DeepSeek V4 Pro, Mistral Large3, and Sarvam M. They score anonymous and identity-disclosed responses from three primary models on 58 factual, reasoning, political, and preference-based questions. Identity disclosure slightly raises scores for factual questions, moderately affects stress-reasoning tasks, and causes large changes for geopolitically sensitive topics. Notable results include GLM5.1 (+7.00 points, p = 0.0249) and Llama 3.3 70B (+1.56 points, p = 0.00). We also introduce a blockchain-based commit-reveal protocol using Autonomous Economic Agents on an Ethereum-compatible ledger. In Phase 1, each judge records a one-way hash of its score and a secret salt before candidate identities are revealed. In Phase 2, the identity and raw score are disclosed and verified on-chain. This creates a tamper-evident audit trail that separates blind evaluation from post-hoc claims and reduces the verification burden on independent researchers and leaderboard operators.

Closing the AI Trust Gap: The Case for Independent Certification for Trustworthy AI

Independent, outcome-oriented certification is proposed as the connective layer that can close the trust gap, complementing regulation and internal governance by making trustworthiness measurable, comparable, and commercially rewarded.