DeepAI AI Chat
Log In Sign Up

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

by   Haishan Ye, et al.
Peking University
The Hong Kong University of Science and Technology

Zeroth-order optimization or derivative-free optimization is an important research topic in machine learning. In recent, 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 Hessian 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 of such. Our empirical studies on the black-box adversarial attack problem validate that our algorithm can achieve improved success rates with a lower query complexity.


A Frank-Wolfe Framework for Efficient and Effective Adversarial Attacks

Depending on how much information an adversary can access to, adversaria...

A Zeroth-Order Block Coordinate Descent Algorithm for Huge-Scale Black-Box Optimization

We consider the zeroth-order optimization problem in the huge-scale sett...

AutoZOOM: Autoencoder-based Zeroth Order Optimization Method for Attacking Black-box Neural Networks

Recent studies have shown that adversarial examples in state-of-the-art ...

Distributed Black-Box Optimization via Error Correcting Codes

We introduce a novel distributed derivative-free optimization framework ...

On the Design of Black-box Adversarial Examples by Leveraging Gradient-free Optimization and Operator Splitting Method

Robust machine learning is currently one of the most prominent topics wh...

Zeroth-Order Stochastic Variance Reduction for Nonconvex Optimization

As application demands for zeroth-order (gradient-free) optimization acc...

Optimization of circuitry arrangements for heat exchangers using derivative-free optimization

Optimization of the refrigerant circuitry can improve a heat exchanger's...