放射性数据:通过培训进行追踪
Radioactive data: tracing through training
摘要:
我们想要检测特定的图像数据集是否已被用于训练模型。我们提出了一种新的技术,\emph{radioactive data},它对这个数据集进行了不可察觉的更改,这样在它上面训练的任何模型都将带有可识别的标记。该标记对不同架构或优化方法等强烈变化具有鲁棒性。给定一个经过训练的模型,我们的技术可以检测放射性数据的使用,并提供一定的置信度(p值)。我们使用标准架构(Resnet-18、VGG-16、Densenet-121)和训练程序在大规模基准测试(Imagenet)上进行的实验表明,即使用于训练模型的数据中只有1%是放射性的,我们也可以以高置信度(p<10^-4)检测放射性数据的使用。我们的方法对数据增强和深度网络优化的随机性具有鲁棒性。因此,它提供了比数据中毒和后门方法更高的信噪比。
英文摘要:
We want to detect whether a particular image dataset has been used to train a model. We propose a new technique, \emph{radioactive data}, that makes imperceptible changes to this dataset such that any model trained on it will bear an identifiable mark. The mark is robust to strong variations such as different architectures or optimization methods. Given a trained model, our technique detects the use of radioactive data and provides a level of confidence (p-value). Our experiments on large-scale benchmarks (Imagenet), using standard architectures (Resnet-18, VGG-16, Densenet-121) and training procedures, show that we can detect usage of radioactive data with high confidence (p<10^-4) even when only 1% of the data used to trained our model is radioactive. Our method is robust to data augmentation and the stochasticity of deep network optimization. As a result, it offers a much higher signal-to-noise ratio than data poisoning and backdoor methods.
机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。