2 papers
cs.LG2026
CHiQPM: Calibrated Hierarchical Interpretable Image Classification
Thomas Norrenbrock, Timo Kaiser, Sovan Biswas +3
Globally interpretable models are a promising approach for trustworthy AI in safety-critical domains. Alongside global explanations, detailed local explanations are a crucial compl…
cs.AI2025
Is It Certainly a Deepfake? Reliability Analysis in Detection & Generation Ecosystem
Neslihan Kose, Anthony Rhodes, Umur Aybars Ciftci +1
As generative models are advancing in quality and quantity for creating synthetic content, deepfakes begin to cause online mistrust. Deepfake detectors are proposed to counter this…