Adaptive Inter-Modality Attention for Enhanced Cross-Domain Deepfake Detection Transferability

Cross-domain generalization remains a critical challenge in deepfake detection, with existing methods exhibiting severe performance degradation across unseen generative architectures. We propose CAMME (Cross-domain Adaptive Multi-Modal Embeddings), which dynamically integrates visual, textual, and frequency-domain features via embedding-level multi-modal self-attention. Treating each modality as a distinct sequence element enables cross-modal interactions that adaptively weight discriminative features based on input characteristics. Unlike static fusion approaches, CAMME learns input-specific contributions, dynamically emphasizing optimal signals across visual semantics, textual consistency, and spectral artifacts. Evaluation across twelve generative architectures demonstrates superior cross-domain performance: 77.34% average F1-score on natural scenes (7.30% improvement) and 66.46% on facial datasets (13.25% improvement). CAMME exhibits exceptional robustness with 14.7% Attack Success Rate against seven prominent adversarial attacks (4-6× improvement) and 96.63% accuracy under natural perturbations. Ablation results confirm the importance of each modality and the effectiveness of our inter-modal attention over standard fusion methods.