Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes
Autor: | Shukla, Satya Narayan, Sahu, Anit Kumar, Willmott, Devin, Kolter, J. Zico |
---|---|
Rok vydání: | 2020 |
Předmět: | |
Druh dokumentu: | Working Paper |
Popis: | 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 $\ell_\infty$ and $\ell_2$ 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. Comment: Accepted at KDD 2021. arXiv admin note: substantial text overlap with arXiv:1909.13857 |
Databáze: | arXiv |
Externí odkaz: |