论文标题
基于模型的无衍生化方法，用于黑盒对抗示例：Bobyqa
A Model-Based Derivative-Free Approach to Black-Box Adversarial Examples: BOBYQA
论文作者
论文摘要
我们证明，基于模型的自由优化算法可以使用少于非基于模型的方法来生成对对抗性的靶向错误分类。具体来说，我们考虑了黑框设置，并证明网络查询的数量通过减少允许的$ \ ell^{\ elfty} $扰动能量来使任务更具挑战性的影响较小，或者通过防御对抗性错误分类来培训网络。我们通过将基于遗传，组合和直接搜索算法的最先进的对抗性靶向错误分类方法与BobyQA算法与最先进的对抗性靶向错误分类方法进行对比来说明这一点。我们观察到，对于高$ \ ell^{\ infty} $ Energy扰动，上述简单的无模型方法需要最少的查询。相比之下，当扰动能量降低或针对对抗性扰动训练网络时，提出的基于BobyQA的方法可实现最先进的结果。
We demonstrate that model-based derivative free optimisation algorithms can generate adversarial targeted misclassification of deep networks using fewer network queries than non-model-based methods. Specifically, we consider the black-box setting, and show that the number of networks queries is less impacted by making the task more challenging either through reducing the allowed $\ell^{\infty}$ perturbation energy or training the network with defences against adversarial misclassification. We illustrate this by contrasting the BOBYQA algorithm with the state-of-the-art model-free adversarial targeted misclassification approaches based on genetic, combinatorial, and direct-search algorithms. We observe that for high $\ell^{\infty}$ energy perturbations on networks, the aforementioned simpler model-free methods require the fewest queries. In contrast, the proposed BOBYQA based method achieves state-of-the-art results when the perturbation energy decreases, or if the network is trained against adversarial perturbations.
