Investigating the Adversarial Robustness of Density Estimation Using the Probability Flow ODE
This addresses security concerns for density estimation in diffusion models, though it is incremental as it focuses on evaluating existing methods under attacks.
The paper investigated the robustness of density estimation using probability flow ODEs against gradient-based attacks, finding that it remains robust against high-complexity attacks on CIFAR-10, with some adversarial samples being semantically meaningful.
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.