Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes

Authors: Satya Narayan Shukla, Anit Kumar Sahu, Devin Willmott, J. Zico Kolter
Published: 2020-07-13 | Updated: 2021-06-11

Source: https://arxiv.org/abs/2007.07210

PDF: https://arxiv.org/pdf/2007.07210

Labels Predicted by AI

攻撃手法 深層学習 次元削減手法

Please note that these labels were automatically added by AI. Therefore, they may not be entirely accurate.
For more details, please see the About the Literature Database page.

Abstract

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label (hard label) to a queried data input. We propose a simple and efficient Bayesian Optimization (BO) based approach for developing black-box adversarial attacks. Issues with BO’s performance in high dimensions are avoided by searching for adversarial examples in a structured low-dimensional subspace. We demonstrate the efficacy of our proposed attack method by evaluating both ℓ_∞ and ℓ₂ norm constrained untargeted and targeted hard label black-box attacks on three standard datasets – MNIST, CIFAR-10 and ImageNet. Our proposed approach consistently achieves 2x to 10x higher attack success rate while requiring 10x to 20x fewer queries compared to the current state-of-the-art black-box adversarial attacks.