**LLMs respond differently to harmful prompts when AI watermarking is used** >

**LLMs respond differently to harmful prompts when AI watermarking is used**

> SynthID can cause models to follow harmful instructions they would otherwise refuse. THE PROVENANCE TAX LLMs respond differently to harmful prompts when AI watermarking is used SynthID can cause models to follow harmful instructions they would otherwise refuse. Dan Goodin – Sep 17, 2026 2:33 pm | 33 AI generated content warning watermark isolated on white background Credit: Getty Images AI generated content warning w...

**来源信息**
- **来源**：Hacker News：AI 热帖
- **分类**：论文
- **发布时间**：2026-09-18 15:02（北京时间）
- **原文**：[打开原文](https://arstechnica.com/security/2026/09/ai-text-watermarking-can-make-models-more-vulnerable-to-adversarial-prompts)