SpecRNet: Towards Faster and More Accessible Audio DeepFake Detection

TL;DR

SpecRNet is a fast, low-resource neural network architecture for audio DeepFake detection, achieving comparable accuracy to state-of-the-art models while significantly reducing inference time, making it more accessible for widespread use.

Contribution

The paper introduces SpecRNet, a novel neural network architecture that offers faster inference and lower computational requirements for audio DeepFake detection without sacrificing accuracy.

Findings

SpecRNet reduces processing time by up to 40% compared to LCNN.

SpecRNet maintains performance comparable to top DeepFake detection models.

Benchmarks confirm SpecRNet's effectiveness across various low-resource and attack scenarios.

Abstract

Audio DeepFakes are utterances generated with the use of deep neural networks. They are highly misleading and pose a threat due to use in fake news, impersonation, or extortion. In this work, we focus on increasing accessibility to the audio DeepFake detection methods by providing SpecRNet, a neural network architecture characterized by a quick inference time and low computational requirements. Our benchmark shows that SpecRNet, requiring up to about 40% less time to process an audio sample, provides performance comparable to LCNN architecture - one of the best audio DeepFake detection models. Such a method can not only be used by online multimedia services to verify a large bulk of content uploaded daily but also, thanks to its low requirements, by average citizens to evaluate materials on their devices. In addition, we provide benchmarks in three unique settings that confirm the correctness of our model. They reflect scenarios of low-resource datasets, detection on short utterances and limited attacks benchmark in which we take a closer look at the influence of particular attacks on given architectures.