arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2310.07084cs.LG
收藏

探究使用概率流ODE的密度估计的对抗鲁棒性

Investigating the Adversarial Robustness of Density Estimation Using the Probability Flow ODE

Intel Labs(英特尔实验室)

Marius Arvinte, Cory Cornelius, Jason Martin, Nageen Himayat

AI总结:

本文研究基于概率流ODE的密度估计模型对梯度似然最大化攻击的鲁棒性,提出六种攻击方法(含反向积分攻击),在CIFAR-10上验证其对高复杂度攻击的鲁棒性。

摘要:

除了令人印象深刻的采样能力外,基于分数的扩散模型还提供了一种强大的分析工具,即对训练数据分布下的查询样本进行无偏密度估计。在本工作中,我们研究了使用概率流(PF)神经常微分方程(ODE)模型进行密度估计时,针对基于梯度的似然最大化攻击的鲁棒性,以及其与样本复杂度的关系,其中样本的压缩大小被用作其复杂度的度量。我们引入并评估了六种基于梯度的对数似然最大化攻击,包括一种新颖的反向积分攻击。我们在CIFAR-10上的实验评估表明,使用PF ODE的密度估计对高复杂度、高似然攻击具有鲁棒性,并且在某些情况下,对抗样本具有语义上的意义,正如对鲁棒估计器所预期的那样。

英文摘要:

Beyond their impressive sampling capabilities, score-based diffusion models offer a powerful analysis tool in the form of unbiased density estimation of a query sample under the training data distribution. In this work, we investigate the robustness of density estimation using the probability flow (PF) neural ordinary differential equation (ODE) model against gradient-based likelihood maximization attacks and the relation to sample complexity, where the compressed size of a sample is used as a measure of its complexity. We introduce and evaluate six gradient-based log-likelihood maximization attacks, including a novel reverse integration attack. Our experimental evaluations on CIFAR-10 show that density estimation using the PF ODE is robust against high-complexity, high-likelihood attacks, and that in some cases adversarial samples are semantically meaningful, as expected from a robust estimator.

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。

↑