arXiv cs.CV
· Papers
What Do Deepfake Benchmarks Measure? An Audit Using Frozen Self-Supervised Representations
arXiv:2606.26384v1 Announce Type: new Abstract: As deepfake generators approach perceptual indistinguishability, reliable detection becomes critical. Yet, detectors that score well on benchmarks routinely fail in the wild. A concerning feedback loop has emerged: benchmarks drive increasingly complex, engineered detecto