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

Authors:
  • SJShan Jia
    Shan Jia
  • RLReilin Lyu
    Reilin Lyu
  • KZKangran Zhao
    Kangran Zhao
  • YCYize Chen
    Yize Chen
  • ZYZhiyuan Yan
    Zhiyuan Yan
  • YJYan Ju
    Yan Ju
  • CHChuanbo Hu
    Chuanbo Hu
  • XLXin Li
    Xin Li
  • BWBaoyuan Wu
    Baoyuan Wu
  • SLSiwei Lyu
    Siwei Lyu

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, 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.