Can I read Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks on EtoBox?

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks by Li, Huichen; Li, Linyi; Xu, Xiaojun; Zhang, Xiaolu; Yang, Shuang; Li, Bo is a scholarly article available to read on EtoBox.

What is Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks about?

Gradient estimation and vector space projection have been studied as two distinct topics. We aim to bridge the gap between the two by investigating how to efficiently estimate gradient based on a projected low-dimensional space. We first provide lower and upper bounds for gradient estimation under both linear and nonlinear projections, and outline checkable sufficient conditions under which one is better than the other. Moreover, we analyze the query complexity for the projection-based gradient estimation and present a sufficient condition for query-efficient estimators. Built upon our theoretic analysis, we propose a novel query-efficient Nonlinear Gradient Projection-based Boundary Blackbox Attack (NonLinear-BA). We conduct extensive experiments on four image datasets: ImageNet, CelebA, CIFAR-10, and MNIST, and show the superiority of the proposed methods compared with the state-of-the-art baselines. In particular, we show that the projection-based boundary blackbox attacks are able to achieve much smaller magnitude of perturbations with 100% attack success rate based on efficient queries. Both linear and nonlinear projections demonstrate their advantages under different conditio

Author

Li, Huichen; Li, Linyi; Xu, Xiaojun; Zhang, Xiaolu; Yang, Shuang; Li, Bo

Published

2021

Language

EN