mlsanityData to 14 Oct 2026

Optimizing One-pixel Black-box Adversarial Attacks

arXiv 2205.02116 ↗First posted 30 Apr 2022cs.CR cs.LGcited by 0

Not on the map. Why?

Abstract (arXiv)

The output of Deep Neural Networks (DNN) can be altered by a small perturbation of the input in a black box setting by making multiple calls to the DNN. However, the high computation and time required makes the existing approaches unusable. This work seeks to improve the One-pixel (few-pixel) black-box adversarial attacks to reduce the number of calls to the network under attack. The One-pixel attack uses a non-gradient optimization algorithm to find pixel-level perturbations under the constraint of a fixed number of pixels, which causes the network to predict the wrong label for a given image. We show through experimental results how the choice of the optimization algorithm and initial positions to search can reduce function calls and increase attack success significantly, making the attack more practical in real-world settings.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 23 references that are in the map. First posted on arXiv 30 Apr 2022.

Builds on

18 of 23 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2013Intriguing properties of neural networkscited by 5,155
  3. 2016Adversarial examples in the physical worldcited by 1,769
  4. 2014Deep Neural Networks are Easily Fooled: High Confidence Predictions for Unrecognizable Imagescited by 776
  5. 2017ZOO: Zeroth Order Optimization based Black-box Attacks to Deep Neural Networks without Training Substitute Modelscited by 666
  6. 2017One pixel attack for fooling deep neural networkscited by 582
  7. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 536
  8. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  9. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 462
  10. 2020Torchattacks: A PyTorch Repository for Adversarial Attackscited by 158
  11. 2020Physically Realizable Adversarial Examples for LiDAR Object Detectioncited by 137
  12. 2018Query-Efficient Hard-label Black-box Attack:An Optimization-based Approachcited by 130
6 more
  1. 2017On the Robustness of Semantic Segmentation Models to Adversarial Attackscited by 126
  2. 2019Improving Black-box Adversarial Attacks with a Transfer-based Priorcited by 121
  3. 2018Structured Adversarial Attack: Towards General Implementation and Better Interpretabilitycited by 64
  4. 2019Towards Adversarially Robust Object Detectioncited by 55
  5. 2013Optimal parameter selection for the alternating direction method of multipliers (ADMM): quadratic problemscited by 19
  6. 2020Influence of Initialization on the Performance of Metaheuristic Optimizerscited by 5

Built on by

Not cited yet.