The paper introduces a training‑free proactive defense for detecting partial deepfake speech by using self‑embedding steganography. It embeds a compressed version of the clean audio within itself, allowing post‑hoc extraction of reference content and enabling detection of spoofed segments via codec‑based restoration. Experiments on a benchmark dataset show that this method complements passive detectors and operates without any training, offering a robust, data‑efficient alternative for partial deepfake detection.
By Yigitcan \"Ozer, Zhe Zhang, Wanying Ge, Xin Wang, Junichi Yamagishi
Partial manipulation of speech recordings, where only localized segments of an utterance are altered, poses a significant challenge for content integrity verification, as reliable detection and locali...
arXiv:2608. 09593v1 Announce Type: cross Abstract: Recent advances in speech synthesis and audio generation have made high-fidelity acoustic forgery low-cost and difficult to attribute, enabling a realistic attack scenario in which speech and background audio are independently manipulated over otherwise authentic video.
By Yanqiu Li, Yang Xiao, Jisheng Bai, Bin Chen, Hong Jia, Ting Dang
CRAW is a codec‑robust audio watermarking framework designed to embed imperceptible signals into synthetic speech, enabling provenance verification. It improves robustness against neural re‑synthesis, codecs, denoisers, and vocoders while preserving perceptual quality through distortion‑aware training, attention‑based pooling, perceptual masking, and error‑correcting codes. Experiments show CRAW outperforms existing post‑hoc watermarking methods in robustness without compromising audio quality.
Audio watermarking aims to embed identifiable information into audio while remaining imperceptible. Existing methods adopt high-fidelity, low-energy designs to preserve perceptual quality, but the resulting watermarks lack robustness under suppression by speech reconstruction models.
The paper introduces CRAW, a codec‑robust audio watermarking framework designed to embed imperceptible signals into synthetic speech. CRAW enhances robustness against neural re‑synthesis, codecs, denoisers, and vocoders while preserving high perceptual quality through distortion‑aware training, attention‑based pooling, perceptual masking, and error‑correcting codes. Experiments show CRAW outperforms existing post‑hoc watermarking methods in robustness without compromising audio quality.
By David Chernin, Ethan Fetaya
arXiv:2607. 01729v1 Announce Type: new Abstract: Deep learning models for speech classification are vulnerable to backdoor attacks, where malicious triggers cause misclassification at inference time.
By Yueming Huang, Wenhan Yao, Fen Xiao, Xiarun Chen, Weiping Wen
arXiv:2606. 29544v1 Announce Type: cross Abstract: We present Proteus, a framework developed at Resemble AI for automated robustness testing of our audio deepfake detection system.
By Nicolas M. M\"uller, Aditya Tirumala Bukkapatnam, Zohaib Ahmed
The paper introduces Traceable TTS, a framework that enables Text‑to‑Speech systems to attribute synthesized speech to their source models without embedding explicit watermarks. By jointly training the TTS model and a discriminator, the method improves traceability generalization while maintaining or slightly enhancing audio quality. This represents the first attempt at watermark‑free TTS with strong traceability, and the authors plan to release the code to support further research.
By Yuxiang Zhao, Yunchong Xiao, Yushen Chen, Zhikang Niu, Shuai Wang, Kai Yu, Xie Chen
The paper formalizes backward compatibility for zero‑bit neural audio watermarking and introduces a training framework that pairs a new detector with a sequence of frozen legacy embedders. Using a performance‑weighted sampling strategy, the detector maintains accuracy across all earlier versions, but this coupling can cause an embedder‑collapse effect that degrades the true negative rate against out‑of‑chain embedders. To mitigate this, an Angular Diversity Loss is added, ensuring each new embedder occupies a distinct output space region and restoring near‑perfect true negative rates without harming detection accuracy or audio quality.
By Admir Krni\'c, Kosta Pavlovi\'c, Petar Nedi\'c, \v{Z}eljko Bolevi\'c, Slavko Kova\v{c}evi\'c, Igor Djurovi\'c
arXiv:2606. 11828v1 Announce Type: cross Abstract: Audio watermarking aims to embed identifiable information into audio while remaining imperceptible.
By Haiyun Li, Shuhai Peng, Zhisheng Zhang, Jingran Xie, Xiaofeng Xie, Hanyang Peng, Zhiyong Wu
Provenance watermarking is increasingly treated as a safeguard for synthetic speech, whether built directly into speech-generation models such as Chatterbox, provided through dedicated techniques such as AudioSeal, or deployed by commercial platforms such as ElevenLabs. We identify a previously uncharacterized liability: when synthetic speech is watermarked and human speech is not, detectors trained alongside latch onto the watermark as a spurious "watermark => fake" shortcut.