• Home
  • Search
  • Practical Black-Box Attacks against Machine Learning
  • Open Access IconOpen Access
  • Cite Icon4177
  • https://doi.org/10.1145/3052973.3053009Copy DOI Icon

Practical Black-Box Attacks against Machine Learning

  • Apr 2, 2017
  • Nicolas Papernot +5 more
Show More
  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Machine learning (ML) models, e.g., deep neural networks (DNNs), are vulnerable to adversarial examples: malicious inputs modified to yield erroneous model outputs, while appearing unmodified to human observers. Potential attacks include having malicious content like malware identified as legitimate or controlling vehicle behavior. Yet, all existing adversarial example attacks require knowledge of either the model internals or its training data. We introduce the first practical demonstration of an attacker controlling a remotely hosted DNN with no such knowledge. Indeed, the only capability of our black-box adversary is to observe labels given by the DNN to chosen inputs. Our attack strategy consists in training a local model to substitute for the target DNN, using inputs synthetically generated by an adversary and labeled by the target DNN. We use the local substitute to craft adversarial examples, and find that they are misclassified by the targeted DNN. To perform a real-world and properly-blinded evaluation, we attack a DNN hosted by MetaMind, an online deep learning API. We find that their DNN misclassifies 84.24% of the adversarial examples crafted with our substitute. We demonstrate the general applicability of our strategy to many ML techniques by conducting the same attack against models hosted by Amazon and Google, using logistic regression substitutes. They yield adversarial examples misclassified by Amazon and Google at rates of 96.19% and 88.94%. We also find that this black-box attack strategy is capable of evading defense strategies previously found to make adversarial example crafting harder.

Similar Papers
  • Book Chapter
  • Citations7

Attack on Deep Steganalysis Neural Networks

  • Jan 01, 2018
  • Shiyu Li +5
  • Conference Article
  • Citations26

Detecting Adversarial Examples Using Data Manifolds

  • Oct 01, 2018
  • Susmit Jha +3
  • Conference Article
  • Citations12

Nickel to Lego

  • Nov 06, 2019
  • Joon Kuy Han +2
  • Research Article
  • Citations1

Generating watermarked adversarial texts

  • Mar 28, 2023
  • Journal of Electronic Imaging
  • Mingjie Li +3
  • Research Article
  • Citations21

A lightweight unsupervised adversarial detector based on autoencoder and isolation forest

  • Nov 19, 2023
  • Pattern Recognition
  • Hui Liu +4
  • Research Article
  • Citations3

Amplification trojan network: Attack deep neural networks by amplifying their inherent weakness

  • Jul 16, 2022
  • Neurocomputing
  • Zhanhao Hu +3
  • Research Article
  • Citations2

Restoration of Adversarial Examples Using Image Arithmetic Operations

  • Jan 01, 2022
  • Intelligent Automation & Soft Computing
  • Kazim Ali +1
  • PDF
  • Research Article
  • Citations33

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

  • Jun 03, 2019
  • Applied Sciences
  • Xianfeng Gao +4
  • 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
  • Conference Article
  • Citations8

Schmidt: Image Augmentation for Black-Box Adversarial Attack

  • Jul 01, 2018
  • Yucheng Shi +1
  • PDF
  • Research Article
  • Citations67

Assessing Optimizer Impact on DNN Model Sensitivity to Adversarial Examples

  • Jan 01, 2019
  • IEEE Access
  • Yixiang Wang +5
  • Conference Article
  • Citations10

Fooling a Neural Network in Military Environments: Random Untargeted Adversarial Example

  • Oct 01, 2018
  • Hyun Kwon +3
  • 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
  • Research Article
  • Citations10

SA-ES: Subspace Activation Evolution Strategy for Black-Box Adversarial Attacks

  • Jun 01, 2023
  • IEEE Transactions on Emerging Topics in Computational Intelligence
  • Zhenhua Li +4
  • Research Article

Transfer-based Adversarial Attack with Rectified Adam and Color Invariance

  • Jan 01, 2022
  • International Journal of Software and Informatics
  • Jia Ding +1
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.