Hessian-Aware Zeroth-Order Optimization for Black-Box Adversarial Attack

Authors: Haishan Ye, Zhichao Huang, Cong Fang, Chris Junchi Li, Tong Zhang
Published: 2018-12-29 | Updated: 2019-03-20

Source: https://arxiv.org/abs/1812.11377

PDF: https://arxiv.org/pdf/1812.11377

Labels Predicted by AI

マシン・アンラーニング 収束性分析 深層学習

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

Zeroth-order optimization is an important research topic in machine learning. In recent years, it has become a key tool in black-box adversarial attack to neural network based image classifiers. However, existing zeroth-order optimization algorithms rarely extract second-order information of the model function. In this paper, we utilize the second-order information of the objective function and propose a novel Hessian-aware zeroth-order algorithm called ZO-HessAware. Our theoretical result shows that ZO-HessAware has an improved zeroth-order convergence rate and query complexity under structured Hessian approximation, where we propose a few approximation methods for estimating Hessian. Our empirical studies on the black-box adversarial attack problem validate that our algorithm can achieve improved success rates with a lower query complexity.