English(EN) Backward Compatibility in Zero-Bit Neural Audio Watermarking

新框架正式化了神经网络音频水印的向后兼容性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-16 04:00

研究人员正式化了零比特神经网络音频水印中的向后兼容性概念，解决了更新的嵌入器和检测器会破坏检测或增加误报率的问题。一个新的训练框架将检测器与冻结的旧版嵌入器配对，使用性能加权采样策略来跨版本保持准确性。为了对抗嵌入器崩溃并保持对未识别嵌入器的真实负例率，引入了角度多样性损失（ADL），迫使新的嵌入器进入不同的输出空间区域，而不会牺牲检测准确性或音频质量。 AI

影响引入了一种提高神经网络音频水印系统对抗更新的鲁棒性和安全性。

排序理由关于神经网络音频水印新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 14 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 关于神经网络音频水印新方法的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, other; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Breaking (< 6h); Fresh story with cross-source coverage still developing. Ranking may shift as more sources report.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.LG TIER_1 English(EN) · Admir Krni\'c, Kosta Pavlovi\'c, Petar Nedi\'c, \v{Z}eljko Bolevi\'c, Slavko Kova\v{c}evi\'c, Igor Djurovi\'c · 2026-10-16 04:00

零比特神经网络音频水印中的向后兼容性

arXiv:2610.22296v1 Announce Type: cross Abstract: Neural watermarking systems are typically trained as tightly coupled embedder-detector pairs and implicitly assume static deployment. In real-world deployments, embedders and detectors are frequently updated and selectively decoup…

本文如何被排名

报道来源 [1]

零比特神经网络音频水印中的向后兼容性

相关实体

相关话题