PulseAugur
实时 08:34:26

新的水印技术将信号嵌入生成模型动态中

研究人员开发了一种新颖的生成模型水印技术,该技术将信号直接嵌入到学习到的连续动态中,特别是流匹配模型的速度场。该方法将水印制定为在连续信道上的随机编码,在训练过程中添加一个依赖于密钥的扰动,该扰动不会改变生成的分布。在MNIST和CIFAR-10等标准数据集上的实验表明,该方法可以可靠地恢复消息并保持生成质量,而在没有密钥的情况下,解码准确率会下降到随机水平。 AI

影响 引入了一种新的生成模型水印方法,有望增强内容溯源和安全性。

排序理由 该集群包含一篇详细介绍生成模型新技术的学术论文。[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 →

新的水印技术将信号嵌入生成模型动态中

本文如何被排名

Signal score
0 / 100
Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket
Tool
该集群包含一篇详细介绍生成模型新技术的学术论文。[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, safety
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
121 days old
Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准

报道来源 [1]

  1. arXiv cs.LG TIER_1 English(EN) · Shuchan Wang ·

    具有随机码的流匹配模型的动态级水印

    We introduce a dynamics-level approach to watermarking generative models. Rather than embedding signals into model weights or outputs, we embed the watermark directly into the learned continuous dynamics -- the velocity field of a flow matching model. We formulate this as random …