Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
3
0
3
0
DeepSSIM++ reveals that you can achieve a 46-point boost in memorization detection accuracy without sacrificing computational efficiency in medical generative models.
HexMIL achieves a remarkable +9.1 AUC and +9.4 F1 score improvement in detecting unseen medical deepfakes, setting a new standard for interpretability in AI-driven medical imaging.
Training deepfake detectors solely on real images can lead to significantly better generalization across unseen generator types.