Advance Fake Video Detection via Vision Transformers
Gespeichert in:
| Titel: | Advance Fake Video Detection via Vision Transformers |
|---|---|
| Autoren: | Joy Battocchio, Stefano Dell'Anna, Andrea Montibeller, Giulia Boato |
| Quelle: | Proceedings of the ACM Workshop on Information Hiding and Multimedia Security. :1-11 |
| Publication Status: | Preprint |
| Verlagsinformationen: | ACM, 2025. |
| Publikationsjahr: | 2025 |
| Schlagwörter: | FOS: Computer and information sciences, Artificial Intelligence (cs.AI), Computer Science - Artificial Intelligence, Computer Vision and Pattern Recognition (cs.CV), Computer Science - Computer Vision and Pattern Recognition, Multimedia forensics, AI-generated video detection, vision transformers, latent video diffusion models, deepfakes, Computer Science - Multimedia, Multimedia (cs.MM) |
| Beschreibung: | Recent advancements in AI-based multimedia generation have enabled the creation of hyper-realistic images and videos, raising concerns about their potential use in spreading misinformation. The widespread accessibility of generative techniques, which allow for the production of fake multimedia from prompts or existing media, along with their continuous refinement, underscores the urgent need for highly accurate and generalizable AI-generated media detection methods, underlined also by new regulations like the European Digital AI Act. In this paper, we draw inspiration from Vision Transformer (ViT)-based fake image detection and extend this idea to video. We propose an {original} %innovative framework that effectively integrates ViT embeddings over time to enhance detection performance. Our method shows promising accuracy, generalization, and few-shot learning capabilities across a new, large and diverse dataset of videos generated using five open source generative techniques from the state-of-the-art, as well as a separate dataset containing videos produced by proprietary generative methods. |
| Publikationsart: | Article Conference object |
| DOI: | 10.1145/3733102.3733129 |
| DOI: | 10.48550/arxiv.2504.20669 |
| Zugangs-URL: | http://arxiv.org/abs/2504.20669 |
| Rights: | CC BY |
| Dokumentencode: | edsair.doi.dedup.....50d299d936c5cf5e1ba687e35495643f |
| Datenbank: | OpenAIRE |
Nájsť tento článok vo Web of Science | Abstract: | Recent advancements in AI-based multimedia generation have enabled the creation of hyper-realistic images and videos, raising concerns about their potential use in spreading misinformation. The widespread accessibility of generative techniques, which allow for the production of fake multimedia from prompts or existing media, along with their continuous refinement, underscores the urgent need for highly accurate and generalizable AI-generated media detection methods, underlined also by new regulations like the European Digital AI Act. In this paper, we draw inspiration from Vision Transformer (ViT)-based fake image detection and extend this idea to video. We propose an {original} %innovative framework that effectively integrates ViT embeddings over time to enhance detection performance. Our method shows promising accuracy, generalization, and few-shot learning capabilities across a new, large and diverse dataset of videos generated using five open source generative techniques from the state-of-the-art, as well as a separate dataset containing videos produced by proprietary generative methods. |
|---|---|
| DOI: | 10.1145/3733102.3733129 |