Meta 的最新論文證明，將兩把隱藏水印金鑰合併為一個虛擬金鑰，可在 AI 文字生成時保持多樣性，同時大幅提升偵測成功率。
- 方法：TextSeal2 將兩把金鑰融合，並加入新噪聲，確保每個 token 帶有完整訊號。
AI 伴隨問答
針對這篇報導有疑問？可直接點選快捷問題或向 AI 追問背景脈絡與技術細節：
New Meta paper shows that blending 2 secret keys into 1 makes hidden watermarks in AI-written text easier to detect, even when the AI uses a common trick (like speculative decoding) to write faster.
Watermarks hide a secret-key signal in which tokens an LLM samples, so a detector can later flag its text. Meta's earlier TextSeal picked 1 of 2 keys per token at random, so detection had to average both and lost signal.
TextSeal2 blends both keys into 1 virtual key plus fresh noise, so answers stay varied and every token carries full signal. For speculative decoding, it picks replacement tokens from the leftovers of the drafts' random races, so acceptance rates stay unchanged.
On Qwen3.5-9B with speculative decoding and equal diversity, it detected 89% of 200-token answers at a 0.1% false-positive rate. TextSeal caught 71% and textGrain 67%, at the same acceptance rate.