This technical report studies differentially private release of Kernel SHAP explanations under input-level and background-record privacy models. The main certified contribution is a pure ε-differentially private ranking-release mechanism for Kernel SHAP feature attributions. The mechanism uses the exponential mechanism to release the top-ranked feature, or sequential top-k features, under any valid upper bound Δ∞ on the per-coordinate ranking sensitivity. Its utility is governed by the dimensionless ratio Δ∞/g, where g is the top-1/top-2 attribution-magnitude gap. The report gives analytic Δ∞ certificates for linear models, conservative bounds for logistic models, and diagnostic empirical estimates for nonlinear models. The report also analyzes why full-vector Gaussian release of Kernel SHAP explanations has poor utility in practical regimes, and includes a bootstrap-calibrated full-vector baseline. This bootstrap mechanism is reported as a heuristic and conditional baseline only: it is not claimed to be a certified worst-case differential privacy mechanism unless additional dominance and smoothness assumptions are proven. The manuscript includes theoretical results, threat-model and certification tables, top-1 and top-k ranking-release mechanisms, composition accounting, empirical diagnostics on tabular benchmarks, and a discussion of limitations and open problems.