Explainability in artificial intelligence is crucial for restoring trust, particularly in areas like face forgery detection, where viewers often struggle to distinguish between real and fabricated content.

Inlight ofthis, weproposeanewtraining algorithm called PDE that efficiently enhances the model's robustness for a better worst-group performance.

Learning Rate Warmup is a popular heuristic for training neural networks, especially at larger batch sizes, despite limited understanding of its benefits.

Here,onelineof the literature proposes to train a binary classifier using the human-written texts and LGTs [20,6].