arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2003.00177eess.SPcs.CRcs.LG
收藏

针对线性回归的最优特征操作攻击

Optimal Feature Manipulation Attacks Against Linear Regression

University of California, Davis(加州大学戴维斯分校);Shenzhen Research Institute of Big Data(深圳市大数据研究院)

Fuwei Li, Lifeng Lai, Shuguang Cui

摘要:

在本文中,我们研究如何通过添加精心设计的中毒数据点的数据集或修改原始数据点,通过线性回归获得的系数进行操作。在给定能量预算的情况下,我们首先给出了当目标是修改一个指定的回归系数时最优中毒数据点的封闭解。然后,我们将分析扩展到更具挑战性的场景,其中攻击者的目标是改变一个特定的回归系数,同时使其他回归系数尽可能小地改变。对于这种情况下,我们引入了半定松弛方法来设计最佳的攻击方案。最后,我们研究了一个更强大的对手谁可以执行一个秩一修改的特征矩阵。我们提出了一种交替优化方法来找到最佳的秩一修改矩阵。数值例子说明了本文的分析结果。

英文摘要:

In this paper, we investigate how to manipulate the coefficients obtained via linear regression by adding carefully designed poisoning data points to the dataset or modify the original data points. Given the energy budget, we first provide the closed-form solution of the optimal poisoning data point when our target is modifying one designated regression coefficient. We then extend the analysis to the more challenging scenario where the attacker aims to change one particular regression coefficient while making others to be changed as small as possible. For this scenario, we introduce a semidefinite relaxation method to design the best attack scheme. Finally, we study a more powerful adversary who can perform a rank-one modification on the feature matrix. We propose an alternating optimization method to find the optimal rank-one modification matrix. Numerical examples are provided to illustrate the analytical results obtained in this paper.

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。

↑