open-source-toolkit

SkillMarker 提出一种基于 KGW 的水印方法，用于 AI Agent 技能的所有权验证与泄露追踪，在保证技能功能与事实准确性的同时嵌入强水印信号，并开源了包含嵌入、审计与检测的工具包。

SynthSentry introduces a corpus-level, model-agnostic method to detect synthetic data contamination in language model training data without access to generating models, using distributional divergence over lexical, n-gram, and perplexity statistics.