A Trustworthy Watermarking Framework for LLM-Generated Food Safety Content

2026-09-06

AI Summary

为解决AI生成食品安全内容易被篡改问题，提出ToSS方法，通过自适应双水印技术保证内容完整性和可追溯性。

Abstract

Large language models are transforming many industries with their text generation abilities. However, their outputs can be easily tampered with, creating serious risks in critical areas such as food safety reporting. To protect the integrity and traceability of AI-generated content, this paper introduces ToSS (Token Oriented Repartitioning and Strategic Selection), a reliable authentication method using adaptive dual watermarking. The key innovation of ToSS is its dual watermark encoding approach that divides vocabulary tokens into black and white sublists, enabling precise bit-level embedding of traceability information. Additionally, an entropy adaptive mechanism dynamically selects text regions with high prediction uncertainty for watermark insertion, maintaining text fluency and factual accuracy while ensuring reliable traceability. Experiments on multiple datasets, including food domain texts, demonstrate that ToSS achieves leading performance in both watermark capacity and decoding accuracy.

Problem

• large language models
• content tampering
• food safety reporting
• integrity and traceability

Innovation

• Dual Watermark Encoding
• Token Oriented Repartitioning
• Entropy Adaptive Mechanism
• Traceability Information Embedding