The Consistency Radius is introduced, a metric that quantifies the maximum distribution shift under which an audit conclusion based on a third-party dataset remains consistent, and a convex relaxation-based optimization method to estimate the radius using only model responses over the audit dataset is proposed.
This work forms fairness auditing as a min-max optimization between a computationally unbounded company and a budget-constrained auditor, and demonstrates that increasing audit resources reduces, but does not eliminate, the scope for post-audit manipulation.
Rachit Verma, P. Manisha, Sujit Gujar· 0 citations
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
An auditing protocol is constructed 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).
Rosa Elysabeth Ralinirina, J. Ralaivao, Niaiko Michaël Ralaivao et al.· 0 citations
A novel defense framework is introduced 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 and evaluates 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
A blockchain-based commit-reveal protocol using Autonomous Economic Agents on an Ethereum-compatible ledger 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.
This study identifies the factors that make auditors either willing or unwilling to trust in AI-powered audit processes and addresses the gap in the literature regarding AI auditing by focusing on the practical conditions for building trust in uncertain audit settings.
Joseph Serghani· Arab Economic and Business J...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
