测试模型是否训练过特定数据，揭示AI训练透明性问题。
MINT-Demo: Membership Inference Test Demonstrator
- 通过实验检测模型是否使用了特定数据进行训练。
- 在5个数据库2200万图像上实现最高89%识别准确率。
- 提供演示平台，推动机器学习训练过程透明化。
我们提出会员身份推断测试演示系统（MINT-Demo），强调更透明的机器学习训练过程的重要性。MINT是一种实验性技术，用于判断某些数据是否被用于机器学习模型的训练。我们在多个主流人脸识别模型上进行了实验，使用包含超过2200万张图像的5个公开数据库。实验结果表明，最高可达到89%的准确率，说明识别模型是否使用特定数据训练是可行的。最后，我们构建了一个MINT演示平台，展示该技术，旨在促进人工智能训练过程的透明度。
原文摘要 · Abstract (English)
We present the Membership Inference Test Demonstrator, to emphasize the need for more transparent machine learning training processes. MINT is a technique for experimentally determining whether certain data has been used during the training of machine learning models. We conduct experiments with popular face recognition models and 5 public databases containing over 22M images. Promising results, up to 89% accuracy are achieved, suggesting that it is possible to recognize if an AI model has been trained with specific data. Finally, we present a MINT platform as demonstrator of this technology aimed to promote transparency in AI training.
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。