New Research Targets Demographic Fairness Gaps in Deepfake Detection Models
A new arXiv paper proposes intersectional invariant learning to address performance disparities in deepfake detection, where models show high overall accuracy but uneven results across demographic groups.
Read the full story at arXiv cs.CV ↗
Timeline · 1 report
- 2026-10-30 04:00 · arXiv cs.CV
Intersectional Invariant Learning for Fair Deepfake Detection