Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?

ArXi:2604.02532v1 Announce Type: cross Post-hoc feature attribution methods are widely deployed in safety-critical vision systems, yet their stability under realistic input perturbations remains poorly characterized. Existing metrics evaluate explanations primarily under additive noise, collapse stability to a single scalar, and fail to condition on prediction preservation, conflating explanation fragility with model sensitivity. We