Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917690384318464 |
|---|---|
| author | Jia, Shan Lyu, Reilin Zhao, Kangran Chen, Yize Yan, Zhiyuan Ju, Yan Hu, Chuanbo Li, Xin Wu, Baoyuan Lyu, Siwei |
| author_facet | Jia, Shan Lyu, Reilin Zhao, Kangran Chen, Yize Yan, Zhiyuan Ju, Yan Hu, Chuanbo Li, Xin Wu, Baoyuan Lyu, Siwei |
| contents | DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation. Detecting DeepFakes is currently solved with programmed machine learning algorithms. In this work, we investigate the capabilities of multimodal large language models (LLMs) in DeepFake detection. We conducted qualitative and quantitative experiments to demonstrate multimodal LLMs and show that they can expose AI-generated images through careful experimental design and prompt engineering. This is interesting, considering that LLMs are not inherently tailored for media forensic tasks, and the process does not require programming. We discuss the limitations of multimodal LLMs for these tasks and suggest possible improvements. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14077 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics Jia, Shan Lyu, Reilin Zhao, Kangran Chen, Yize Yan, Zhiyuan Ju, Yan Hu, Chuanbo Li, Xin Wu, Baoyuan Lyu, Siwei Artificial Intelligence Cryptography and Security DeepFakes, which refer to AI-generated media content, have become an increasing concern due to their use as a means for disinformation. Detecting DeepFakes is currently solved with programmed machine learning algorithms. In this work, we investigate the capabilities of multimodal large language models (LLMs) in DeepFake detection. We conducted qualitative and quantitative experiments to demonstrate multimodal LLMs and show that they can expose AI-generated images through careful experimental design and prompt engineering. This is interesting, considering that LLMs are not inherently tailored for media forensic tasks, and the process does not require programming. We discuss the limitations of multimodal LLMs for these tasks and suggest possible improvements. |
| title | Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics |
| topic | Artificial Intelligence Cryptography and Security |
| url | https://arxiv.org/abs/2403.14077 |