---
id: 20261006-T0-15
title: "Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation"
url: https://ai.daily.yangsir.net/daily/20261006-T0-15
issue_date: 2026-10-06
publish_date: 2026-10-05T04:00:00.000Z
source_name: "arXiv cs.AI"
source_url: https://arxiv.org/abs/2610.02300
---

# Keep It CALM: Analyzing the Limits of Global Unsafety in Text-to-Image Generation

arXiv:2610.02300v1 Announce Type: new Abstract: Training-free safeguards for text-to-image generation often rely on a reusable safety signal, such as an unsafe direction or global toxic subspace, applied broadly across prompts. We provide a controlled geometric analysis of this global-unsafety assum

---

**来源**：[arXiv cs.AI](https://arxiv.org/abs/2610.02300)

**详情页**：https://ai.daily.yangsir.net/daily/20261006-T0-15

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*