Hugging Face Trending Papers

The Watermark Shortcut: How Provenance Marking Sabotages Audio Deepfake Detection

Read the original on Hugging Face Trending Papers →

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.

Summary generated by The Flow from the publisher's feed. The full article lives at Hugging Face Trending Papers.

arXiv AI
Aug 11

MADBench: A Benchmark for Modality-Aware Audio Deepfake Detection

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