DiffFace-Edit: A Diffusion-Based Facial Dataset for Forgery-Semantic Driven Deepfake Detection Analysis

TL;DR

This paper introduces DiffFace-Edit, a large-scale facial dataset with fine-grained manipulations across multiple regions, and analyzes the impact of detector-evasive splice attacks on deepfake detection models.

Contribution

The creation of a novel, extensive dataset with region-specific facial edits and the first analysis of splice attack impacts on detection models.

Findings

Over two million AI-generated fake images included.

Multi-region and combined edits increase detection challenge.

Analysis reveals significant impact of splice attacks on model performance.

Abstract

Generative models now produce imperceptible, fine-grained manipulated faces, posing significant privacy risks. However, existing AI-generated face datasets generally lack focus on samples with fine-grained regional manipulations. Furthermore, no researchers have yet studied the real impact of splice attacks, which occur between real and manipulated samples, on detectors. We refer to these as detector-evasive samples. Based on this, we introduce the DiffFace-Edit dataset, which has the following advantages: 1) It contains over two million AI-generated fake images. 2) It features edits across eight facial regions (e.g., eyes, nose) and includes a richer variety of editing combinations, such as single-region and multi-region edits. Additionally, we specifically analyze the impact of detector-evasive samples on detection models. We conduct a comprehensive analysis of the dataset and propose a cross-domain evaluation that combines IMDL methods. Dataset will be available at https://github.com/ywh1093/DiffFace-Edit.