论文标题
低查询预算制度中的简单有效的硬标签黑盒对抗攻击
Simple and Efficient Hard Label Black-box Adversarial Attacks in Low Query Budget Regimes
论文作者
论文摘要
我们专注于黑框对抗攻击的问题，其目的是为深度学习模型生成对抗性示例，仅基于限于输出标签〜（硬标签）的信息来查询数据输入。我们提出了一种简单有效的贝叶斯优化〜基于开发黑盒对抗攻击的方法。通过在结构化的低维子空间中搜索对抗性示例，可以避免BO在高维度中的性能的问题。我们通过评估$ \ ell_ \ infty $和$ \ ell_2 $ norm限制了未靶向和针对性的硬标签的黑色标签攻击（MNIST，MNIST，CIFAR-10和Imagenet），证明了我们提出的攻击方法的功效。我们提出的方法始终达到2倍至10倍的攻击成功率，而与当前最新的黑盒对抗性攻击相比，查询需要少10倍至20倍。
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.
