Muhammad Zabil Mehboob

Does Federated Training Degrade Explainability? A Comparative Analysis of Grad-CAM Faithfulness in Centralized vs. Federated Deepfake Detection

It is found that the relationship between federation and explanation quality is non-monotonic: at near-IID and moderate heterogeneity, federated models match or exceed the faithfulness of a centralized baseline, but at extreme heterogeneity, explanations break down entirely, becoming spatially incoherent and, on averag...