Jul 2026· World Journal of Advanced Research and Reviews· 0 citations
TL;DR
A Supervisory Explainable AI (XAI) Toolkit is proposed, a privacy-preserving auditing platform inspired by the BIS Innovation Hub's Project Noor that equips regulators to independently probe and assess proprietary AI models without requiring firms to surrender raw data, model weights, or trade secrets.
Abstract
Financial supervisors increasingly face artificial intelligence (AI) systems whose internal logic they cannot directly inspect, forcing prudential and conduct regulators to rely on the disclosures, model documentation, and self-attested fairness testing of the firms they oversee. This dependency creates an information asymmetry that undermines effective oversight of credit scoring, anti-money laundering (AML), fraud detection, and insurance-underwriting models. This paper proposes a Supervisory Explainable AI (XAI) Toolkit, a privacy-preserving auditing platform inspired by the Bank for International Settlements (BIS) Innovation Hub's Project Noor, that equips regulators to independently probe and assess proprietary AI models without requiring firms to surrender raw data, model weights, or trade secrets. The toolkit combines a privacy-preserving query broker built on differential privacy, secure multi-party computation, and trusted execution environments with a model-agnostic explainability engine and a fairness-and-robustness metric compiler, translating opaque model logic into standardized, comparable supervisory metrics. We present the system architecture, a five-stage audit workflow, and an illustrative evaluation that quantifies the divergence between firm-reported and independently audited fairness scores across four financial use cases, together with the trade-off between privacy budget and audit fidelity. The results suggest that self-disclosed fairness metrics can materially overstate model fairness and that a modest privacy budget is sufficient to recover most of the audit signal needed for supervisory decision-making. We discuss governance, legal, and technical implications for deploying such toolkits within existing supervisory technology (SupTech) programs and outline directions for standardization and cross-border regulatory cooperation.
A novel audit protocol designed to significantly increase the post-audit detectability of manipulations by enabling the auditor to query the model in an oblivious manner and providing theoretical guarantees showing that, under this protocol, a provider attempting to hide unfairness must falsify a significantly larger number of responses.
Augustin Godinot, Sofiane Azogagh, Julien Ferry et al.· 0 citations
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
Temitope Onibaniyi, Umar Lawal· Texila international journal...· 0 citations
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.
Maraz Mia, Shovan Roy, M. M. Pritom et al.· 0 citations
Artificial intelligence agents can transact online on behalf of a human principal---browsing, paying, receiving, and reviewing---without revealing who that principal is. That architecture starves algorithmic discrimination of its inputs---identity, purchase history, location history, behavioral traces, and demographic proxies---but also forecloses its proof. Disparate-treatment needs comparators; disparate-impact needs protected-class baselines; and *Iqbal*-era pleading needs specific factual allegations---doctrinal predicates that anonymous transactions never generate. The effects fall asymmetrically: those most vulnerable to discrimination are least able to afford the shield and, when harms remain, least able to prove them. The challenge for the law shifts from detecting and remedying algorithmic discrimination to governing agent-mediated anonymity as civil rights infrastructure: ensuring access to privacy-preserving agents, regulating abuse without forced identification, and deciding whether retailers may refuse to deal with agents at all.
Cloud environments built on Amazon Web Services face a structural security vulnerability: once a credential passes authentication, the resulting session is often treated as trusted for its entire duration. This assumption fails when credentials are stolen. We introduce the Explainable Adaptive Zero Trust Framework (EAZTF), a cloud-native security layer that continuously reevaluates the legitimacy of API actions throughout a session. EAZTF combines Isolation Forest and XGBoost to evaluate eight CloudTrail and IAM-derived behavioral features in real time and produce a Trust Risk Score (TRS) that determines whether a session continues, requires step-up MFA, or is restricted. Each decision is accompanied by a SHAP or LIME explanation, providing human-readable audit records for security analysis and compliance. The framework is also evaluated against four adversarial evasion strategies: credential theft, behavioral mimicry, API rate evasion, and privilege escalation. Experiments on an 8,500-record synthetic CloudTrail dataset show that Isolation Forest achieves 94.4% precision, 91.2% recall, and an F1 score of 0.928. Across the four adversarial scenarios, the mean detection rate is 91.0%, with behavioral mimicry being the most difficult at 83.9%. SHAP analysis identifies IP reputation, login-time deviation, and API call velocity as the three dominant features. A structured NIST SP 800-207 self-assessment gives EAZTF a mean compliance score of 93%, compared with 38% for a traditional perimeter baseline. Mean time to detect decreases from hours to under one minute. Because the evaluation uses synthetic data, these results should be interpreted as indicative rather than validated production performance.
Om Singh, Yagyaraj Pandey, Nandini Pathak· 0 citations
Artificial intelligence (AI) agents increasingly need credentials such as application programming interface (API) keys and Secure Shell (SSH) credentials, but placing those secrets in the agent process exposes them to prompt injection, tool misuse, and exfiltration through ordinary agent outputs. We present CapSeal, a capability-based broker that replaces direct secret access with session-bound, non-exportable handles. Agents request policy-evaluated actions, while the broker performs credential-bearing Hypertext Transfer Protocol (HTTP) and SSH execution through typed executors with schema validation, replay protection, revocation epochs, and tamper-evident audit logging. We extend this design to hosted settings where the broker operator is not trusted with tenant secrets. Our main contribution is operator-blind secret mediation: a split-broker architecture in which a small trusted tenant gateway cooperates with an untrusted operator service that stores the master secret only as a fully homomorphic encryption (FHE) ciphertext and evaluates per-request derivations without decrypting it. We formalize the model and prove computational operator blindness from indistinguishability under chosen-plaintext attack (IND-CPA) security of the FHE scheme, together with conditional capability binding for any secure pseudorandom function/message authentication code (PRF/MAC) instantiation. We implement an end-to-end TFHE-rs prototype that exercises split-broker derivation, multi-tenant revocation and rate limiting, audit integration, and HTTP/SSH mediation. The prototype uses a non-cryptographic homomorphic stand-in and measures the cost of crossing the operator-untrusted boundary at about 9 s per request, roughly 17 million times slower than the plaintext path. We also give LowMC and Rasta transciphering designs and compare FHE with trusted execution environment (TEE)- and secure multiparty computation (MPC)-based alternatives, positioning each trust boundary by assurance and performance.
Shutong Jin, Ruiyi Guo, Ray C. C. Cheung· Mathematics· 0 citations