Generalized Design Choices for Deepfake Detectors

TL;DR

This paper systematically investigates how various implementation choices affect deepfake detector performance, aiming to establish best practices that improve accuracy and generalization across different models.

Contribution

It identifies key design factors influencing deepfake detection effectiveness, providing architecture-agnostic guidelines to enhance future model development.

Findings

Certain data preprocessing techniques significantly boost detection accuracy.

Optimized training strategies improve model generalization.

Best practices enable state-of-the-art results on AI-GenBench.

Abstract

The effectiveness of deepfake detection methods often depends less on their core design and more on implementation details such as data preprocessing, augmentation strategies, and optimization techniques. These factors make it difficult to fairly compare detectors and to understand which factors truly contribute to their performance. To address this, we systematically investigate how different design choices influence the accuracy and generalization capabilities of deepfake detection models, focusing on aspects related to training, inference, and incremental updates. By isolating the impact of individual factors, we aim to establish robust, architecture-agnostic best practices for the design and development of future deepfake detection systems. Our experiments identify a set of design choices that consistently improve deepfake detection and enable state-of-the-art performance on the AI-GenBench benchmark.