User Analysis
Analysis of our primary users: AI researchers and journalists.
Main features chosen after user analysis: Retrainability, Ease of use, Explainability and Relevance
Inference
Verify the authenticity of audio files by uploading it and running an inference process.
Select models based on detailed information provided on Veritas.
Retraining
Retraining models for new deepfake audio types is now simpler. Upload a zip file with the dataset, adjust parameters, and start training
VeritasAlpha achieves state-of-the-art performance, merging strengths of different models, enhancing EER by 30%.
VeritasSG is trained for the Singaporean accent using our retraining feature. It detects Singaporean accent deepfakes better than current market models.
VeritasAlpha achieved state-of-the-art performance with the lowest Equal Error Rate (EER) seen. VeritasSG achieves an EER of 0 with the Singaporean Accent audio file.
Software Architecture
User Feedback
We collected responses from approximately 100 users, comprising 50% AI researchers, 40% general public, and 10% journalists using Maze
Found it easy to authenticate audio file
Found highlighting potential deepfaked portions useful
Navigated through the software to retrain models easily
