PVLM: Parsing-Aware Vision-Language Model With Dynamic Contrastive Learning for Zero-Shot Deepfake Attribution

Summary

PVLM is a parsing-aware vision-language model with dynamic contrastive learning for zero-shot deepfake attribution, meaning it traces forged faces to generators not seen in training, including diffusion models. The authors build a fine-grained ZS-DFA benchmark and use face parsing to exploit differences in how GAN and diffusion generators preserve source facial attributes. They report that the model exceeds the state of the art on the ZS-DFA benchmark across various protocol evaluations.

Topics

• Deepfakes and impersonation
• Multimodal models