• Home
  • Search
  • Boosting Targeted Black-Box Attacks via Ensemble Substitute Training and Linear Augmentation
  • Open Access IconOpen Access
  • Cite Icon33
  • https://doi.org/10.3390/app9112286Copy DOI Icon

Boosting Targeted Black-Box Attacks via Ensemble Substitute Training and Linear Augmentation

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

These years, Deep Neural Networks (DNNs) have shown unprecedented performance in many areas. However, some recent studies revealed their vulnerability to small perturbations added on source inputs. Furthermore, we call the ways to generate these perturbations’ adversarial attacks, which contain two types, black-box and white-box attacks, according to the adversaries’ access to target models. In order to overcome the problem of black-box attackers’ unreachabilities to the internals of target DNN, many researchers put forward a series of strategies. Previous works include a method of training a local substitute model for the target black-box model via Jacobian-based augmentation and then use the substitute model to craft adversarial examples using white-box methods. In this work, we improve the dataset augmentation to make the substitute models better fit the decision boundary of the target model. Unlike the previous work that just performed the non-targeted attack, we make it first to generate targeted adversarial examples via training substitute models. Moreover, to boost the targeted attacks, we apply the idea of ensemble attacks to the substitute training. Experiments on MNIST and GTSRB, two common datasets for image classification, demonstrate our effectiveness and efficiency of boosting a targeted black-box attack, and we finally attack the MNIST and GTSRB classifiers with the success rates of 97.7% and 92.8%.

Loading PDF

Similar Papers
  • Research Article
  • Citations3

FCDM: A Methodology Based on Sensor Pattern Noise Fingerprinting for Fast Confidence Detection to Adversarial Attacks

  • Jan 31, 2020
  • IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems
  • Yazhu Lan +6
  • Research Article
  • Citations2

Defending against Adversarial Attacks in Deep Learning with Robust Auxiliary Classifiers Utilizing Bit-plane Slicing

  • Jul 31, 2022
  • ACM Journal on Emerging Technologies in Computing Systems
  • Yuan Liu +2
  • Research Article
  • Citations7

Distillation-Based Cross-Model Transferable Adversarial Attack for Remote Sensing Image Classification

  • May 13, 2025
  • Remote Sensing
  • Xiyu Peng +2
  • Research Article

Transfer-based Adversarial Attack with Rectified Adam and Color Invariance

  • Jan 01, 2022
  • International Journal of Software and Informatics
  • Jia Ding +1
  • PDF
  • Research Article
  • Citations8

A CMA-ES-Based Adversarial Attack on Black-Box Deep Neural Networks

  • Jan 01, 2019
  • IEEE Access
  • Xiaohui Kuang +5
  • PDF
  • Research Article
  • Citations6

Partial Retraining Substitute Model for Query-Limited Black-Box Attacks

  • Oct 14, 2020
  • Applied Sciences
  • Hosung Park +2
  • Conference Article
  • Citations4177

Practical Black-Box Attacks against Machine Learning

  • Apr 02, 2017
  • Nicolas Papernot +5
  • Conference Article
  • Citations15

Adversarial Attacks to Solar Power Forecast

  • Dec 01, 2021
  • Ningkai Tang +2
  • Conference Article
  • Citations43

Adversarial Example Detection by Classification for Deep Speech Recognition

  • Apr 17, 2020
  • Saeid Samizade +3
  • Conference Article
  • Citations164

QEBA: Query-Efficient Boundary-Based Blackbox Attack

  • Jun 01, 2020
  • Huichen Li +4
  • PDF
  • Research Article
  • Citations7

A Hybrid Adversarial Attack for Different Application Scenarios

  • May 21, 2020
  • Applied Sciences
  • Xiaohu Du +6
  • Conference Article
  • Citations20

Adversarial Attacks and Defenses

  • Aug 20, 2020
  • Han Xu +3
  • Research Article
  • Citations16

Consensus Adversarial Defense Method Based on Augmented Examples

  • Jan 01, 2023
  • IEEE Transactions on Industrial Informatics
  • Xintao Ding +4
  • Research Article
  • Citations34

SMGEA: A New Ensemble Adversarial Attack Powered by Long-Term Gradient Memories.

  • Mar 01, 2022
  • IEEE Transactions on Neural Networks and Learning Systems
  • Zhaohui Che +7
  • Research Article
  • Citations6

Timing Black-Box Attacks: Crafting Adversarial Examples through Timing Leaks against DNNs on Embedded Devices

  • Jul 09, 2021
  • IACR Transactions on Cryptographic Hardware and Embedded Systems
  • Tsunato Nakai +2
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.