Beyond Verification: Abductive Explanations for Post-AI Assessment of Privacy Leakage
This work addresses privacy risks in AI auditing for stakeholders needing interpretable tools, though it is incremental with computational challenges.
The paper tackled the problem of privacy leakage in AI-based decision processes by proposing a formal framework using abductive explanations to audit and identify minimal evidence that could disclose sensitive information, with experimental results on the German Credit Dataset showing how sensitive features affect leakage.
Privacy leakage in AI-based decision processes poses significant risks, particularly when sensitive information can be inferred. We propose a formal framework to audit privacy leakage using abductive explanations, which identifies minimal sufficient evidence justifying model decisions and determines whether sensitive information disclosed. Our framework formalizes both individual and system-level leakage, introducing the notion of Potentially Applicable Explanations (PAE) to identify individuals whose outcomes can shield those with sensitive features. This approach provides rigorous privacy guarantees while producing human understandable explanations, a key requirement for auditing tools. Experimental evaluation on the German Credit Dataset illustrates how the importance of sensitive literal in the model decision process affects privacy leakage. Despite computational challenges and simplifying assumptions, our results demonstrate that abductive reasoning enables interpretable privacy auditing, offering a practical pathway to reconcile transparency, model interpretability, and privacy preserving in AI decision-making.