On the Adversarial Robustness of Linear Regression
On the Adversarial Robustness of Linear Regression
复制标题
关于线性回归的对抗鲁棒性
DOI：
10.1109/mlsp49062.2020.9231839
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Cui, Shuguang
中科院分区：
文献类型：
--
作者：
Li, Fuwei;Lai, Lifeng;Cui, Shuguang
本文研究了线性回归问题的对抗鲁棒性。具体来说，我们研究了回归系数对敌对数据样本的稳健性。在考虑的模型中，存在一个能够将一个精心设计的对抗性数据样本添加到数据集中的对手。通过利用这个有毒的数据样本，攻击者试图在敌对数据样本的能量约束下提高或降低一个目标回归系数的大小。我们根据目标回归系数、原始数据集和能量预算来描述最优对抗数据样本的精确表达式。我们在合成和真实数据集上的实验表明了我们所提出的对抗策略的效率和最优性。
In this paper, we study the adversarial robustness of linear regression problems. Specifically, we investigate the robustness of the regression coefficients against adversarial data samples. In the considered model, there exists an adversary who is able to add one carefully designed adversarial data sample into the dataset. By leveraging this poisoned data sample, the adversary tries to boost or depress the magnitude of one targeted regression coefficient under the energy constraint of the adversarial data sample. We characterize the exact expression of the optimal adversarial data sample in terms of the targeted regression coefficient, the original dataset and the energy budget. Our experiments with synthetic and real datasets show the efficiency and optimality of our proposed adversarial strategy.
影响因子：
22.7
作者：
Goodfellow, Ian;McDaniel, Patrick;Papernot, Nicolas
通讯作者：
Papernot, Nicolas