Can ChatGPT Detect DeepFakes? A Study of Using Multimodal Large Language Models for Media Forensics
Authors:
- 17 June 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 4324-4333
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.Keywords
All Related Versions
Funding Information
- National Science Foundation
- National Natural Science Foundation of China
This publication has 25 references indexed in Scilit:
- How Good Is ChatGPT at Face Biometrics? A First Look Into Recognition, Soft Biometrics, and ExplainabilityIEEE Access, 2024
- MDTL-NET: Computer-generated image detection based on multi-scale deep texture learningExpert Systems with Applications, 2024
- ChatGPT for digital forensic investigation: The good, the bad, and the unknownForensic Science International: Digital Investigation, 2023
- Explaining Deepfake Detection by Analysing Image Matching2022
- Wavelet-packets for deepfake image analysis and detectionMachine Learning, 2022
- End-to-End Reconstruction-Classification Learning for Face Forgery Detection2022
- Analyzing and Improving the Image Quality of StyleGAN2020
- Face X-Ray for More General Face Forgery Detection2020
- Celeb-DF: A Large-Scale Challenging Dataset for DeepFake Forensics2020
- A Style-Based Generator Architecture for Generative Adversarial Networks2019