English(EN) STEALTH: Steganographic Text Encoding Agnostic to Low-Level Tensor Hardware

新的STEALTH隐写术方案可抵抗软硬件差异

作者 PulseAugur 编辑部 · [1 个来源] · 2026-11-14 05:00

一种名为STEALTH的新隐写术方案已被开发出来，用于隐藏语言模型生成文本中的消息，克服了先前方法的局限性。现有技术在接收者的硬件或软件精度与发送者不同时常常会失败，导致解码错误。STEALTH采用一种新颖的方法，涉及密钥伪随机噪声和通过束搜索解码的无速率脊码，使其能够抵抗这些变化，并能够每token传输更多数据。 AI

影响这项研究可以为通过AI生成文本传输的敏感数据提供更安全的通信渠道。

排序理由详细介绍新技术的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 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: 17 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍新技术的学术论文。[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, 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.AI TIER_1 English(EN) · William Fleshman · 2026-11-14 05:00

STEALTH：一种对低级张量硬件不敏感的隐写文本编码

arXiv:2611.16928v1 Announce Type: cross Abstract: Provably secure linguistic steganography hides a message inside text sampled from a language model, so that without the key, a stegotext is computationally indistinguishable from an honest model sample. Nearly every such scheme as…

本文如何被排名

报道来源 [1]

STEALTH：一种对低级张量硬件不敏感的隐写文本编码

相关实体

相关话题