Search papers, labs, and topics across Lattice.
Monash University
2
0
4
The challenge reveals that explainability in deepfake detection is not just a nice-to-have; it鈥檚 essential for user trust and effective verification in real-world applications.
Deepfake detectors can be tricked into "reasoning" without visual grounding, but DeepfakeJudge offers a way to bootstrap MLLMs to generate faithful explanations and improve detection accuracy.