论文标题
决策树的遗传对手训练
Genetic Adversarial Training of Decision Trees
论文作者
论文摘要
我们提出了一种基于遗传算法的决策树的合奏的新型学习方法，该算法能够训练决策树，以最大程度地提高其准确性和对对抗性扰动的鲁棒性。该学习算法在内部利用了基于抽象解释的决策树的鲁棒性特性的完整形式验证技术，这是一种众所周知的静态程序分析技术。我们在一种称为Meta-Silvae（MS）的工具中实现了这种遗传对抗训练算法，并在对抗性训练中使用的一些参考数据集中对其进行了实验评估。实验结果表明，MS能够训练与竞争并经常在决策树的对抗性训练的最新训练的同时更加紧凑，因此可以解释和高效的树模型上的最新训练。
We put forward a novel learning methodology for ensembles of decision trees based on a genetic algorithm which is able to train a decision tree for maximizing both its accuracy and its robustness to adversarial perturbations. This learning algorithm internally leverages a complete formal verification technique for robustness properties of decision trees based on abstract interpretation, a well known static program analysis technique. We implemented this genetic adversarial training algorithm in a tool called Meta-Silvae (MS) and we experimentally evaluated it on some reference datasets used in adversarial training. The experimental results show that MS is able to train robust models that compete with and often improve on the current state-of-the-art of adversarial training of decision trees while being much more compact and therefore interpretable and efficient tree models.
