English(EN) Multi-Channel Spread-Spectrum Code Watermarking

新的水印技术可将代码归因于 GPT-4.1 和 Llama 4 等大型语言模型

作者 PulseAugur 编辑部 · [2 个来源] · 2026-07-07 08:50

研究人员开发了一种新颖的多通道扩频码水印技术，可以将代码归因于其起源的大型语言模型。这种事后、无需训练的方法提供了 24 位有效载荷，远超以往的方法，并为各种攻击提供了正式的鲁棒性保证。在 GPT-4.1 和 Llama 4 生成的 Python 文件上进行了测试，该水印达到了 100% 的检测准确率，即使在遭受严重损坏和转换攻击的情况下也能保持高准确率。 AI

影响能够更好地跟踪人工智能生成的代码，以确定出处、许可和问责制。

排序理由该集群描述了一篇详细介绍大型语言模型生成代码的新水印技术的学术论文。

在 arXiv cs.LG 阅读 →

AI 生成摘要 · Google Gemini · 来自 2 个来源。我们如何撰写摘要 →

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: Research; 该集群描述了一篇详细介绍大型语言模型生成代码的新水印技术的学术论文。
Source corroboration: 2 independent sources; Multiple independent publishers reporting the same story raises confidence that it's real and newsworthy.
Topics: paper, product; 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: 93 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 [2]

arXiv cs.LG TIER_1 English(EN) · Soohyeon Choi, Debin Gao, Yue Duan · 2026-07-08 04:00

多通道扩频码水印

arXiv:2607.06009v1 Announce Type: cross Abstract: Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need. Generation-time schemes require access to the producing mo…
arXiv cs.LG TIER_1 English(EN) · Yue Duan · 2026-07-07 08:50

多通道扩频码水印

Attributing code to the large language model that produced it is essential for provenance, licensing, and misuse accountability, yet no deployed watermark meets this need. Generation-time schemes require access to the producing model and cannot be applied to third-party code, whi…

本文如何被排名

报道来源 [2]

多通道扩频码水印

多通道扩频码水印

相关实体

相关话题