Boundary Attack++: Query-Efficient Decision-Based Adversarial Attack

04/03/2019
by   Jianbo Chen, et al.
6

Decision-based adversarial attack studies the generation of adversarial examples that solely rely on output labels of a target model. In this paper, decision-based adversarial attack was formulated as an optimization problem. Motivated by zeroth-order optimization, we develop Boundary Attack++, a family of algorithms based on a novel estimate of gradient direction using binary information at the decision boundary. By switching between two types of projection operators, our algorithms are capable of optimizing L_2 and L_∞ distances respectively. Experiments show Boundary Attack++ requires significantly fewer model queries than Boundary Attack. We also show our algorithm achieves superior performance compared to state-of-the-art white-box algorithms in attacking adversarially trained models on MNIST.

READ FULL TEXT

page 8

page 10

page 20

page 21

page 22

page 23

research
09/24/2019

Sign-OPT: A Query-Efficient Hard-label Adversarial Attack

We study the most practical problem setup for evaluating adversarial rob...
research
02/20/2023

Efficient Algorithms for Boundary Defense with Heterogeneous Defenders

This paper studies the problem of defending (1D and 2D) boundaries again...
research
07/05/2022

Query-Efficient Adversarial Attack Based on Latin Hypercube Sampling

In order to be applicable in real-world scenario, Boundary Attacks (BAs)...
research
08/06/2023

CGBA: Curvature-aware Geometric Black-box Attack

Decision-based black-box attacks often necessitate a large number of que...
research
02/25/2021

Nonlinear Projection Based Gradient Estimation for Query Efficient Blackbox Attacks

Gradient estimation and vector space projection have been studied as two...
research
05/09/2021

Automated Decision-based Adversarial Attacks

Deep learning models are vulnerable to adversarial examples, which can f...
research
01/29/2019

RED-Attack: Resource Efficient Decision based Attack for Machine Learning

Due to data dependency and model leakage properties, Deep Neural Network...

Please sign up or login with your details

Forgot password? Click here to reset