Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics

arXiv:2403.14077v2 Announce Type: replace-cross
Abstract: 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, …

algorithms arxiv can capabilities chatgpt cs.ai cs.cr deepfakes detect disinformation forensics generated language language models large machine machine learning machine learning algorithms media study work