Search papers, labs, and topics across Lattice.
3
0
5
49
Embedding watermarks in the latent space of neural codecs can drastically improve robustness, achieving up to 97.1% accuracy in challenging conditions.
PRoVeFL achieves unprecedented efficiency in federated learning, improving runtime by up to 100x while ensuring robust privacy and verifiability.
A new dataset, SynSFX, reveals that existing audio deepfake detectors struggle with generalization to synthetic sound effects, highlighting a critical gap in current research.
