DETER: Detecting Edited Regions for Deterring Generative Manipulations

TL;DR

DETER is a large-scale, diverse dataset designed to improve the detection of various types of manipulated images, addressing limitations of previous datasets and aiding the development of more reliable deep fake detection methods.

Contribution

The paper introduces DETER, a comprehensive dataset with diverse manipulations and realistic fake images, to advance the detection of generative image manipulations.

Findings

Deep fake detection rate is 20.4% lower on DETER compared to other datasets.

DETER includes 300,000 images manipulated by four state-of-the-art generators.

The dataset covers face swapping, inpainting, and attribute editing manipulations.

Abstract

Generative AI capabilities have grown substantially in recent years, raising renewed concerns about potential malicious use of generated data, or "deep fakes". However, deep fake datasets have not kept up with generative AI advancements sufficiently to enable the development of deep fake detection technology which can meaningfully alert human users in real-world settings. Existing datasets typically use GAN-based models and introduce spurious correlations by always editing similar face regions. To counteract the shortcomings, we introduce DETER, a large-scale dataset for DETEcting edited image Regions and deterring modern advanced generative manipulations. DETER includes 300,000 images manipulated by four state-of-the-art generators with three editing operations: face swapping (a standard coarse image manipulation), inpainting (a novel manipulation for deep fake datasets), and attribute editing (a subtle fine-grained manipulation). While face swapping and attribute editing are performed on similar face regions such as eyes and nose, the inpainting operation can be performed on random image regions, removing the spurious correlations of previous datasets. Careful image post-processing is performed to ensure deep fakes in DETER look realistic, and human studies confirm that human deep fake detection rate on DETER is 20.4% lower than on other fake datasets. Equipped with the dataset, we conduct extensive experiments and break-down analysis using our rich annotations and improved benchmark protocols, revealing future directions and the next set of challenges in developing reliable regional fake detection models.