I would also like to ask three question. Do you know how well your model generalizes to video/audio deepfakes created by models that are not within your training sets? And also have you investigated whether your model can be used in a GAN setting to improve a deepfake generator towards creating better fakes? Or how robust your detectors are against adversarial attacks?
1 - We include multiple models for GAN and non-GAN related synthetic media.
2 - Models are only as good as the training data, and most training data breaks down in the real world because hackers have access to this same open source training data. So we create our own proprietary training data which we have automated, and we continuously update it based upon emerging deepfakes that we find in the wild.
3 - We target 95% accuracy with all public and proprietary training sets. And we continuously test and iterate both the data sets and the models.
4 - Our policies require a background check on all users to filter out bad actors. We additionally have technology safeguards in place to limit improper use.