Black-box Adversarial Attacks with Bayesian Optimization

Anonymous

Sep 25, 2019 ICLR 2020 Conference Blind Submission readers: everyone Show Bibtex
  • TL;DR: We show that a relatively simple black-box adversarial attack scheme using Bayesian optimization and dimension upsampling is preferable to existing methods when the number of available queries is very low.
  • Abstract: We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples using information limited to loss function evaluations of input-output pairs. We use Bayesian optimization (BO) to specifically cater to scenarios involving low query budgets to develop query efficient adversarial attacks. We alleviate the issues surrounding BO in regards to optimizing high dimensional deep learning models by effective dimension upsampling techniques. Our proposed approach achieves performance comparable to the state of the art black-box adversarial attacks albeit with a much lower average query count. In particular, in low query budget regimes, our proposed method reduces the query count up to 80% with respect to the state of the art methods.
  • Keywords: black-box adversarial attacks, bayesian optimization
0 Replies

Loading