论文标题
可证明可靠的度量学习
Provably Robust Metric Learning
论文作者
论文摘要
公制学习是分类和相似性搜索算法的重要家族，但是对小型对抗扰动的学识指标的鲁棒性较少。在本文中，我们表明，专注于提高清洁准确性的现有度量学习算法可能导致指标不如欧几里得距离稳定。为了克服这个问题，我们提出了一种新型的度量学习算法，以找到一种与对抗性扰动相稳定的玛哈拉氏症距离，并且可获得模型的鲁棒性是可认证的。实验结果表明，所提出的公制学习算法改善了认证的鲁棒错误和经验性鲁棒错误（对抗性攻击下的错误）。此外，与通常在清洁和鲁棒错误之间遇到权衡取舍的神经网络防御不同，与以前的度量学习方法相比，我们的方法不会牺牲干净的错误。我们的代码可在https://github.com/wangwllu/provase_robust_metric_learning获得。
Metric learning is an important family of algorithms for classification and similarity search, but the robustness of learned metrics against small adversarial perturbations is less studied. In this paper, we show that existing metric learning algorithms, which focus on boosting the clean accuracy, can result in metrics that are less robust than the Euclidean distance. To overcome this problem, we propose a novel metric learning algorithm to find a Mahalanobis distance that is robust against adversarial perturbations, and the robustness of the resulting model is certifiable. Experimental results show that the proposed metric learning algorithm improves both certified robust errors and empirical robust errors (errors under adversarial attacks). Furthermore, unlike neural network defenses which usually encounter a trade-off between clean and robust errors, our method does not sacrifice clean errors compared with previous metric learning methods. Our code is available at https://github.com/wangwllu/provably_robust_metric_learning.
