WaveVerify: A Novel Audio Watermarking Framework for Media Authentication and Combatting Deepfakes

TL;DR

WaveVerify introduces a new audio watermarking framework designed to authenticate media and combat the rising threat of deepfake audio, addressing urgent security and trust issues in synthetic media.

Contribution

The paper presents a novel audio watermarking method specifically tailored for media authentication and deepfake detection, enhancing robustness against sophisticated voice synthesis techniques.

Findings

Effective detection of deepfake audio using WaveVerify

High robustness of watermark against common audio processing attacks

Significant improvement over existing watermarking methods

Abstract

The rapid advancement of voice generation technologies has enabled the synthesis of speech that is perceptually indistinguishable from genuine human voices. While these innovations facilitate beneficial applications such as personalized text-to-speech systems and voice preservation, they have also introduced significant risks, including deepfake impersonation scams and synthetic media-driven disinformation campaigns. Recent reports indicate that in 2024, deepfake fraud attempts surged by over 1,300% compared to 2023, underscoring the urgent need for robust audio content authentication. The financial sector has been particularly impacted, with a loss of over 10 million USD to voice scams and individual victims reporting losses exceeding $6,000 from AI-generated deepfake calls. In response, regulators and governments worldwide are enacting measures to improve AI content transparency and traceability, emphasizing the development of forensic tools and watermarking techniques as essential strategies to uphold media integrity.