Skip to content

An instruction-following dataset for interactive deepfake analysis in ICASSP 2025 accepted paper "Towards Interactive Deepfake Analysis".

License

Notifications You must be signed in to change notification settings

lxq1000/DFA-Instruct

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

4 Commits
 
 
 
 
 
 

Repository files navigation

DFA-Instruct

An instruction-following dataset for interactive deepfake analysis in ICASSP 2025 accepted paper Towards Interactive Deepfake Analysis.

  • Responses generated by the interactive deepfake analysis system, DFA-GPT

Image

  • Data construction process for DFA-Instruct

Image

  • Overall architecture of the DFA-GPT

Image

Abstract: Existing deepfake analysis methods are primarily based on discriminative models, which significantly limit their application scenarios. This paper aims to explore interactive deepfake analysis by performing instruction tuning on multi-modal large language models (MLLMs). This will face challenges such as the lack of datasets and benchmarks, and low training efficiency. To address these issues, we introduce (1) a GPT-assisted data construction process resulting in an instruction-following dataset called DFA-Instruct, (2) a benchmark named DFA-Bench, designed to comprehensively evaluate the capabilities of MLLMs in deepfake detection, deepfake classification, and artifact description, and (3) construct an interactive deepfake analysis system called DFA-GPT, as a strong baseline for the community, with the Low-Rank Adaptation (LoRA) module.

About

An instruction-following dataset for interactive deepfake analysis in ICASSP 2025 accepted paper "Towards Interactive Deepfake Analysis".

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published