Attending Generalizability in Course of Deep Fake Detection by Exploring Multi-task Learning
This work addresses generalizability in deep fake detection for security applications, but appears incremental as it builds on well-studied multi-task and contrastive learning techniques.
The authors tackled the problem of detecting deep fake videos in cross-manipulation scenarios by exploring multi-task learning techniques, achieving a generalized model that accurately detects unseen manipulation methods compared to state-of-the-art approaches.
This work explores various ways of exploring multi-task learning (MTL) techniques aimed at classifying videos as original or manipulated in cross-manipulation scenario to attend generalizability in deep fake scenario. The dataset used in our evaluation is FaceForensics++, which features 1000 original videos manipulated by four different techniques, with a total of 5000 videos. We conduct extensive experiments on multi-task learning and contrastive techniques, which are well studied in literature for their generalization benefits. It can be concluded that the proposed detection model is quite generalized, i.e., accurately detects manipulation methods not encountered during training as compared to the state-of-the-art.