基于程序分析的决策树防规避攻击认证
Certifying Decision Trees Against Evasion Attacks by Program Analysis
摘要：
机器学习已被证明对于一系列不同的任务是非常宝贵的，但它也被证明容易受到规避攻击，即，对输入数据进行恶意的人为扰动，以强制进行错误预测。在本文中，我们提出了一种新的技术来验证决策树模型的安全性，以防止规避攻击的表达威胁模型，其中攻击者可以表示为一个任意的命令式程序。我们的方法利用决策树的可解释性属性，将它们转换为命令式程序，这是适合于传统的程序分析技术。通过利用抽象解释框架，我们能够充分验证在公开数据集上训练的决策树模型的安全保证。我们的实验表明，我们的技术是精确和有效的，只产生最小数量的误报和扩展到的情况下，这是棘手的竞争对手的方法。
英文摘要：
Machine learning has proved invaluable for a range of different tasks, yet it also proved vulnerable to evasion attacks, i.e., maliciously crafted perturbations of input data designed to force mispredictions. In this paper we propose a novel technique to verify the security of decision tree models against evasion attacks with respect to an expressive threat model, where the attacker can be represented by an arbitrary imperative program. Our approach exploits the interpretability property of decision trees to transform them into imperative programs, which are amenable for traditional program analysis techniques. By leveraging the abstract interpretation framework, we are able to soundly verify the security guarantees of decision tree models trained over publicly available datasets. Our experiments show that our technique is both precise and efficient, yielding only a minimal number of false positives and scaling up to cases which are intractable for a competitor approach.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
