{"title":"ASSMark: Dual Defense Against Speech Synthesis Attack via Adversarial Robust Watermarking","authors":"Yulin He;Hongxia Wang;Yiqin Qiu;Hao Cao","doi":"10.1109/LSP.2025.3562817","DOIUrl":null,"url":null,"abstract":"Given the widespread dissemination of digital audio and the advancements in speech synthesis technologies, protecting audio copyright has become a critical issue. Although watermarks play an important role in copyright verification and forensic analysis, they are insufficient to proactively defend against malicious speech synthesis. To address this issue, we introduce a novel adversarial speech synthesis watermarking mechanism (ASSMark), which simultaneously traces the audio copyright and disrupts the speech synthesis models by embedding robust adversarial watermarks in a one-time manner. Specifically, we design a unified training framework that models the embedding of watermarks and adversarial perturbations as collaborative tasks. This approach allows for the fine-tuning of any robust watermark into an adversarial watermark, resulting in watermarked audio that can effectively defend against unauthorized speech synthesis attacks. Experimental results demonstrate that ASSMark achieves over 90% protection rate even to unknown black-box models. Compared to simplistic two-step protection methods, it not only effectively resists synthesis attacks but also achieves superior watermark extraction accuracy and speech quality, offering an outstanding solution for protecting audio copyright.","PeriodicalId":13154,"journal":{"name":"IEEE Signal Processing Letters","volume":"32 ","pages":"1870-1874"},"PeriodicalIF":3.2000,"publicationDate":"2025-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"IEEE Signal Processing Letters","FirstCategoryId":"5","ListUrlMain":"https://ieeexplore.ieee.org/document/10971213/","RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 0
Abstract
Given the widespread dissemination of digital audio and the advancements in speech synthesis technologies, protecting audio copyright has become a critical issue. Although watermarks play an important role in copyright verification and forensic analysis, they are insufficient to proactively defend against malicious speech synthesis. To address this issue, we introduce a novel adversarial speech synthesis watermarking mechanism (ASSMark), which simultaneously traces the audio copyright and disrupts the speech synthesis models by embedding robust adversarial watermarks in a one-time manner. Specifically, we design a unified training framework that models the embedding of watermarks and adversarial perturbations as collaborative tasks. This approach allows for the fine-tuning of any robust watermark into an adversarial watermark, resulting in watermarked audio that can effectively defend against unauthorized speech synthesis attacks. Experimental results demonstrate that ASSMark achieves over 90% protection rate even to unknown black-box models. Compared to simplistic two-step protection methods, it not only effectively resists synthesis attacks but also achieves superior watermark extraction accuracy and speech quality, offering an outstanding solution for protecting audio copyright.
期刊介绍:
The IEEE Signal Processing Letters is a monthly, archival publication designed to provide rapid dissemination of original, cutting-edge ideas and timely, significant contributions in signal, image, speech, language and audio processing. Papers published in the Letters can be presented within one year of their appearance in signal processing conferences such as ICASSP, GlobalSIP and ICIP, and also in several workshop organized by the Signal Processing Society.