PolyGlotFake: A Novel Multilingual and Multimodal DeepFake Dataset

TL;DR

PolyGlotFake is a new multilingual, multimodal deepfake dataset that includes diverse languages and advanced generation techniques, aiming to improve detection methods and reflect current deepfake technology trends.

Contribution

It introduces the first comprehensive multilingual, multimodal deepfake dataset using cutting-edge synthesis techniques, addressing limitations of existing datasets.

Findings

The dataset presents significant challenges for current detection methods.

State-of-the-art detectors show decreased performance on PolyGlotFake.

The dataset enhances research into robust multimodal deepfake detection.

Abstract

With the rapid advancement of generative AI, multimodal deepfakes, which manipulate both audio and visual modalities, have drawn increasing public concern. Currently, deepfake detection has emerged as a crucial strategy in countering these growing threats. However, as a key factor in training and validating deepfake detectors, most existing deepfake datasets primarily focus on the visual modal, and the few that are multimodal employ outdated techniques, and their audio content is limited to a single language, thereby failing to represent the cutting-edge advancements and globalization trends in current deepfake technologies. To address this gap, we propose a novel, multilingual, and multimodal deepfake dataset: PolyGlotFake. It includes content in seven languages, created using a variety of cutting-edge and popular Text-to-Speech, voice cloning, and lip-sync technologies. We conduct comprehensive experiments using state-of-the-art detection methods on PolyGlotFake dataset. These experiments demonstrate the dataset's significant challenges and its practical value in advancing research into multimodal deepfake detection.