提出新方法提升AI文本水印抗篡改能力，有效应对改写等攻击。
Robustness Assessment and Enhancement of Text Watermarking for Google's SynthID
- 融合语义检索与概率水印，在词法和语义层同步嵌入水印
- 在多种攻击下水印识别F1得分平均提升11.1%
- 适合需要防伪造的生成内容溯源场景
谷歌深度求索提出的SynthID-Text文本水印技术为追踪AI生成文本来源提供了有前景的解决方案。然而，我们的鲁棒性评估发现，该方法易受保持语义的攻击（如改写、复制粘贴、反向翻译）影响，导致水印可检测性显著下降。为此，我们提出SynGuard，一种结合语义信息检索（SIR）的语义对齐强度与SynthID-Text的概率水印机制的混合框架。该方法在词汇和语义层面联合嵌入水印，实现语义不变下的鲁棒溯源。在多个攻击场景下的实验表明，SynGuard相比SynthID-Text平均提升11.1%的F1分数。结果证明语义感知水印能有效抵御真实世界篡改。所有代码、数据集及评估脚本已公开于：https://github.com/githshine/SynGuard。
原文摘要 · Abstract (English)
Recent advances in LLM watermarking methods such as SynthID-Text by Google DeepMind offer promising solutions for tracing the provenance of AI-generated text. However, our robustness assessment reveals that SynthID-Text is vulnerable to meaning-preserving attacks, such as paraphrasing, copy-paste modifications, and back-translation, which can significantly degrade watermark detectability. To address these limitations, we propose SynGuard, a hybrid framework that combines the semantic alignment strength of Semantic Information Retrieval (SIR) with the probabilistic watermarking mechanism of SynthID-Text. Our approach jointly embeds watermarks at both lexical and semantic levels, enabling robust provenance tracking while preserving the original meaning. Experimental results across multiple attack scenarios show that SynGuard improves watermark recovery by an average of 11.1\% in F1 score compared to SynthID-Text. These findings demonstrate the effectiveness of semantic-aware watermarking in resisting real-world tampering. All code, datasets, and evaluation scripts are publicly available at: https://github.com/githshine/SynGuard.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。