避开凸诱导分类器的查询策略
Query Strategies for Evading Convex-Inducing Classifiers
摘要：
分类器通常用于检测恶意活动。我们研究了一个对手如何系统地查询分类器，以获取信息，使对手逃避检测，同时产生一个接近最小的成本修改他们的意图渎职。我们将Lowd和Meek（2005）的理论推广到凸诱导分类器家族，该家族将输入空间划分为两个集合，其中一个是凸的。我们目前的查询算法，这个家庭，构建未被发现的情况下，大约最小的成本，只使用多项式多查询的空间的维度和近似的水平。我们的研究结果表明，接近最佳的规避可以完成没有反向工程的分类器的决策边界。我们还考虑了一般的LP成本，并表明，近最佳的规避家庭的凸诱导分类一般是有效的，为所有级别的近似，如果p=1的正凸和负凸。
英文摘要：
Classifiers are often used to detect miscreant activities. We study how an adversary can systematically query a classifier to elicit information that allows the adversary to evade detection while incurring a near-minimal cost of modifying their intended malfeasance. We generalize the theory of Lowd and Meek (2005) to the family of convex-inducing classifiers that partition input space into two sets one of which is convex. We present query algorithms for this family that construct undetected instances of approximately minimal cost using only polynomially-many queries in the dimension of the space and in the level of approximation. Our results demonstrate that near-optimal evasion can be accomplished without reverse-engineering the classifier's decision boundary. We also consider general lp costs and show that near-optimal evasion on the family of convex-inducing classifiers is generally efficient for both positive and negative convexity for all levels of approximation if p=1.
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。
