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

AIにより推定されたラベル

攻撃手法 深層学習 次元削減手法

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

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.