CPSample:用于在扩散过程中保护训练数据的分类器保护采样
CPSample: Classifier Protected Sampling for Guarding Training Data During Diffusion
AI总结:
本研究提出CPSample方法,通过训练过拟合随机二进制标签的分类器引导扩散采样过程,在不降低生成图像质量的前提下防止训练数据复制,计算成本更低且能提升模型抗成员推理攻击能力,还可避免Stable Diffusion出现模式崩溃。
摘要:
扩散模型倾向于精确复制其训练数据,尤其是在小数据集上训练时。大多数先前的工作试图通过施加差分隐私约束或掩码部分训练数据来缓解这个问题,但这会导致图像质量显著大幅下降。我们提出了CPSample,这是一种修改采样过程的方法,既能防止训练数据复制,又能保持图像质量。CPSample利用一个分类器,该分类器被训练成对附加在训练数据上的随机二进制标签过拟合。随后CPSample使用分类器引导,将生成过程引导离开那些可以被高确定性分类的点集——该点集包含训练数据。CPSample在CIFAR-10和CelebA-64上分别取得了4.97和2.97的FID分数,且不会生成训练数据的精确复制品。与旨在保护训练图像的先前方法不同,CPSample只需要训练一个分类器,而不需要重新训练扩散模型,计算成本更低。此外,我们的技术使扩散模型对成员推理攻击具有更强的鲁棒性,成员推理攻击是指对手试图辨别哪些图像在模型的训练数据集中。我们证明CPSample的行为类似于一个内置的拒绝采样器,并展示了它在Stable Diffusion中防止模式崩溃的能力。
英文摘要:
Diffusion models have a tendency to exactly replicate their training data, especially when trained on small datasets. Most prior work has sought to mitigate this problem by imposing differential privacy constraints or masking parts of the training data, resulting in a notable substantial decrease in image quality. We present CPSample, a method that modifies the sampling process to prevent training data replication while preserving image quality. CPSample utilizes a classifier that is trained to overfit on random binary labels attached to the training data. CPSample then uses classifier guidance to steer the generation process away from the set of points that can be classified with high certainty, a set that includes the training data. CPSample achieves FID scores of 4.97 and 2.97 on CIFAR-10 and CelebA-64, respectively, without producing exact replicates of the training data. Unlike prior methods intended to guard the training images, CPSample only requires training a classifier rather than retraining a diffusion model, which is computationally cheaper. Moreover, our technique provides diffusion models with greater robustness against membership inference attacks, wherein an adversary attempts to discern which images were in the model's training dataset. We show that CPSample behaves like a built-in rejection sampler, and we demonstrate its capabilities to prevent mode collapse in Stable Diffusion.
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。