DF-CLIP: Adapting Visual-Language Models for Generalizable Deepfake Detection Using Multi-Modal Prompt Tuning

Lecture notes in computer science 2026

View at publisher

Authors: Wuti Xiong, Valentina Kuklina

DOI: 10.1007/978-981-95-5679-3_37

Cited by: 0

References: 24

Fields of Study & Subjects

Digital Media Forensic Detection Generative Adversarial Networks and Image Synthesis Multimodal Machine Learning Applications

References 24