Towards Interactive Deepfake Analysis

TL;DR

This paper introduces an interactive deepfake analysis framework using instruction-tuned multi-modal large language models, addressing dataset scarcity and efficiency issues, and providing a new benchmark and system for the community.

Contribution

It presents a novel instruction-tuning approach with a new dataset, benchmark, and an interactive analysis system for deepfake detection and explanation.

Findings

Created DFA-Instruct dataset for instruction following

Developed DFA-Bench for comprehensive evaluation

Built DFA-GPT system with LoRA for interactive analysis

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. The dataset and code will be made available at https://github.com/lxq1000/DFA-Instruct to facilitate further research.