Progressive-Scale Boundary Blackbox Attack via Projective Gradient Estimation

06/10/2021
by   Jiawei Zhang, et al.
0

Boundary based blackbox attack has been recognized as practical and effective, given that an attacker only needs to access the final model prediction. However, the query efficiency of it is in general high especially for high dimensional image data. In this paper, we show that such efficiency highly depends on the scale at which the attack is applied, and attacking at the optimal scale significantly improves the efficiency. In particular, we propose a theoretical framework to analyze and show three key characteristics to improve the query efficiency. We prove that there exists an optimal scale for projective gradient estimation. Our framework also explains the satisfactory performance achieved by existing boundary black-box attacks. Based on our theoretical framework, we propose Progressive-Scale enabled projective Boundary Attack (PSBA) to improve the query efficiency via progressive scaling techniques. In particular, we employ Progressive-GAN to optimize the scale of projections, which we call PSBA-PGAN. We evaluate our approach on both spatial and frequency scales. Extensive experiments on MNIST, CIFAR-10, CelebA, and ImageNet against different models including a real-world face recognition API show that PSBA-PGAN significantly outperforms existing baseline attacks in terms of query efficiency and attack success rate. We also observe relatively stable optimal scales for different models and datasets. The code is publicly available at https://github.com/AI-secure/PSBA.

READ FULL TEXT

page 2

page 41

page 42

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
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
11/29/2019

Square Attack: a query-efficient black-box adversarial attack via random search

We propose the Square Attack, a new score-based black-box l_2 and l_∞ ad...
research
05/28/2020

QEBA: Query-Efficient Boundary-Based Blackbox Attack

Machine learning (ML), especially deep neural networks (DNNs) have been ...
research
10/17/2022

Face Pasting Attack

Cujo AI and Adversa AI hosted the MLSec face recognition challenge. The ...
research
11/15/2021

Finding Optimal Tangent Points for Reducing Distortions of Hard-label Attacks

One major problem in black-box adversarial attacks is the high query com...
research
04/04/2022

APP: Anytime Progressive Pruning

With the latest advances in deep learning, there has been a lot of focus...

Please sign up or login with your details

Forgot password? Click here to reset