通过分析模型内部状态，提前检测训练数据泄露风险。
ISACL: Internal State Analyzer for Copyrighted Training Data Leakage
- 在生成前分析模型内部状态，识别潜在版权数据泄露
- 结合RAG系统实现合规生成，泄露风险降低显著
- 适合关注AI版权合规与数据隐私的开发者使用
大型语言模型（LLMs）虽推动了自然语言处理的发展，但存在无意暴露受版权保护或专有数据的风险，尤其当这些数据用于训练却未授权分发时。传统方法仅在内容生成后进行干预，可能导致敏感信息泄露。本文提出一种主动防护策略：在文本生成前分析模型内部状态，以检测潜在泄露风险。基于精心筛选的版权材料数据集，我们训练了一个神经网络分类器，可识别高风险模式，从而在生成过程中及时终止或修改输出，防止信息外泄。该框架已集成至检索增强生成（RAG）系统中，确保符合版权与许可要求，提升数据隐私与伦理标准。实验结果表明，内部状态分析能有效降低版权数据泄露风险，提供可扩展、无缝嵌入现有AI工作流的解决方案，在保障生成质量的同时满足版权合规需求。代码已开源。
原文摘要 · Abstract (English)
Large Language Models (LLMs) have revolutionized Natural Language Processing (NLP) but pose risks of inadvertently exposing copyrighted or proprietary data, especially when such data is used for training but not intended for distribution. Traditional methods address these leaks only after content is generated, which can lead to the exposure of sensitive information. This study introduces a proactive approach: examining LLMs' internal states before text generation to detect potential leaks. By using a curated dataset of copyrighted materials, we trained a neural network classifier to identify risks, allowing for early intervention by stopping the generation process or altering outputs to prevent disclosure. Integrated with a Retrieval-Augmented Generation (RAG) system, this framework ensures adherence to copyright and licensing requirements while enhancing data privacy and ethical standards. Our results show that analyzing internal states effectively mitigates the risk of copyrighted data leakage, offering a scalable solution that fits smoothly into AI workflows, ensuring compliance with copyright regulations while maintaining high-quality text generation. The implementation is available on GitHub.\footnote{https://github.com/changhu73/Internal_states_leakage}
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。