Generalized Design Choices for Deepfake Detectors

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.

Key Contributions

• Systematic, architecture-agnostic empirical study isolating the impact of data augmentation, preprocessing, training duration, and multiclass labeling on deepfake detector generalization
• Evaluation of incremental/continual learning strategies for sample-efficient detector updates as new generative models emerge
• Identification of a 'best of' configuration that achieves state-of-the-art performance on the AI-GenBench benchmark across multiple vision backbones (ResNet-50 CLIP, ViT-L CLIP, DINOv2)

🛡️ Threat Analysis

Details

Similar Papers