MADBench
Explore score history ↗MADBench is a benchmark for modality-aware audio deepfake detection, treating speech and environmental audio as distinct components. It evaluates detectors across independently manipulated forgery sources.
- Released
- 2026-08-10
- Institutions
- The University of Melbourne · Xi’an University of Posts and Telecommunications · University of Auckland
- Evaluates
- Robotics & Embodied AI, Vision & 3D, cs.SD
- Openness
- unknown
- Importer
- Claire Radar
- Review status
- unreviewed
MADBench paper
No reported scores are on record for this benchmark yet.