Boosting Decision-Based Black-Box Adversarial Attack with Gradient Priors

Han Liu, Xingshuo Huang, Xiaotong Zhang, Qimai Li, Fenglong Ma, Wei Wang, Hongyang Chen, Hong Yu, Xianchao Zhang

Research output: Chapter in Book/Report/Conference proceedingConference contribution


Decision-based methods have shown to be effective in black-box adversarial attacks, as they can obtain satisfactory performance and only require to access the final model prediction. Gradient estimation is a critical step in black-box adversarial attacks, as it will directly affect the query efficiency. Recent works have attempted to utilize gradient priors to facilitate score-based methods to obtain better results. However, these gradient priors still suffer from the edge gradient discrepancy issue and the successive iteration gradient direction issue, thus are difficult to simply extend to decision-based methods. In this paper, we propose a novel Decision-based Black-box Attack framework with Gradient Priors (DBA-GP), which seamlessly integrates the data-dependent gradient prior and time-dependent prior into the gradient estimation procedure. First, by leveraging the joint bilateral filter to deal with each random perturbation, DBA-GP can guarantee that the generated perturbations in edge locations are hardly smoothed, i.e., alleviating the edge gradient discrepancy, thus remaining the characteristics of the original image as much as possible. Second, by utilizing a new gradient updating strategy to automatically adjust the successive iteration gradient direction, DBA-GP can accelerate the convergence speed, thus improving the query efficiency. Extensive experiments have demonstrated that the proposed method outperforms other strong baselines significantly.

Original languageEnglish (US)
Title of host publicationProceedings of the 32nd International Joint Conference on Artificial Intelligence, IJCAI 2023
EditorsEdith Elkind
PublisherInternational Joint Conferences on Artificial Intelligence
Number of pages9
ISBN (Electronic)9781956792034
StatePublished - 2023
Event32nd International Joint Conference on Artificial Intelligence, IJCAI 2023 - Macao, China
Duration: Aug 19 2023Aug 25 2023

Publication series

NameIJCAI International Joint Conference on Artificial Intelligence
ISSN (Print)1045-0823


Conference32nd International Joint Conference on Artificial Intelligence, IJCAI 2023

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence

Cite this