用梯度分析判断文本是否被大模型训练过，保护数据隐私。
Is My Text in Your AI Model? Gradient-based Membership Inference Test applied to LLMs
- 通过分析模型梯度判断输入文本是否曾用于训练。
- 在7个模型、6个数据集上AUC达85%~99%。
- 适合关注AI数据安全与合规的开发者和研究人员。
本文将基于梯度的成员推理测试（gMINT）应用于基于Transformer的文本分类任务，以判断特定数据样本是否被用于大语言模型（LLM）的训练。该方法利用梯度信息分析，识别输入文本是否属于训练数据，回应了机器学习中的数据隐私担忧。实验在7个Transformer模型和6个数据集（总计超过250万条句子）上进行，聚焦文本分类任务。结果表明，gMINT具有强鲁棒性，AUC得分在85%至99%之间，具体取决于数据规模和模型架构。研究证明gMINT是一种可扩展、可靠的模型审计工具，有助于提升AI/NLP技术的透明度，保护敏感数据，推动伦理合规部署。
原文摘要 · Abstract (English)
This work adapts and studies the gradient-based Membership Inference Test (gMINT) to the classification of text based on LLMs. MINT is a general approach intended to determine if given data was used for training machine learning models, and this work focuses on its application to the domain of Natural Language Processing. Using gradient-based analysis, the MINT model identifies whether particular data samples were included during the language model training phase, addressing growing concerns about data privacy in machine learning. The method was evaluated in seven Transformer-based models and six datasets comprising over 2.5 million sentences, focusing on text classification tasks. Experimental results demonstrate MINTs robustness, achieving AUC scores between 85% and 99%, depending on data size and model architecture. These findings highlight MINTs potential as a scalable and reliable tool for auditing machine learning models, ensuring transparency, safeguarding sensitive data, and fostering ethical compliance in the deployment of AI/NLP technologies.
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。