Loading [a11y]/accessibility-menu.js
Black-Box Decision based Adversarial Attack with Symmetric α-stable Distribution | IEEE Conference Publication | IEEE Xplore

Black-Box Decision based Adversarial Attack with Symmetric α-stable Distribution


Abstract:

Developing techniques for adversarial attack and defense is an important research field for establishing reliable machine learning and its applications. Many existing met...Show More

Abstract:

Developing techniques for adversarial attack and defense is an important research field for establishing reliable machine learning and its applications. Many existing methods employ Gaussian random variables for exploring the data space to find the most adversarial (for attacking) or least adversarial (for defense) point. However, the Gaussian distribution is not necessarily the optimal choice when the exploration is required to follow the complicated structure that most real-world data distributions exhibit. In this paper, we investigate how statistics of random variables affect such random walk exploration. Specifically, we generalize the Boundary Attack, a state-of-the-art blackbox decision based attacking strategy, and propose the Le'vy-Attack, where the random walk is driven by symmetric α-stable random variables. Our experiments on MNIST and CIFAR10 datasets show that the Le'vy-Attack explores the image data space more efficiently, and significantly improves the performance. Our results also give an insight into the recently found fact in the whitebox attacking scenario that the choice of the norm for measuring the amplitude of the adversarial patterns is essential.
Date of Conference: 02-06 September 2019
Date Added to IEEE Xplore: 18 November 2019
ISBN Information:

ISSN Information:

Conference Location: A Coruna, Spain

References

References is not available for this document.