arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.09279cs.LGstat.ML
收藏

保护回归学习者免受中毒攻击

Defending Regression Learners Against Poisoning Attacks

University of Melbourne(墨尔本大学);Northrop Grumman Corporation(诺斯罗普·格鲁曼公司)

Sandamal Weerasinghe, Sarah M. Erfani, Tansu Alpcan, Christopher Leckie, Justin Kopacz

摘要:

从工程应用到金融预测广泛使用的回归模型容易受到有针对性的恶意攻击,例如训练数据中毒,攻击者可以通过这种攻击操纵其预测。以前的作品,试图解决这个问题依赖于假设的性质的攻击/攻击者或高估的知识的学习者,使他们不切实际。我们引入了一种新的局部内在相似性(LID)为基础的措施称为N-LID,衡量一个给定的数据点的LID相对于其邻居的局部偏差。然后,我们表明,N-LID可以区分中毒样本正常样本,并提出了一个N-LID为基础的防御方法,使攻击者没有假设。通过对基准数据集的大量数值实验,我们表明,所提出的防御机制在预测精度(与未防御的岭模型相比,MSE降低了76%)和运行时间方面优于最先进的防御。

英文摘要:

Regression models, which are widely used from engineering applications to financial forecasting, are vulnerable to targeted malicious attacks such as training data poisoning, through which adversaries can manipulate their predictions. Previous works that attempt to address this problem rely on assumptions about the nature of the attack/attacker or overestimate the knowledge of the learner, making them impractical. We introduce a novel Local Intrinsic Dimensionality (LID) based measure called N-LID that measures the local deviation of a given data point's LID with respect to its neighbors. We then show that N-LID can distinguish poisoned samples from normal samples and propose an N-LID based defense approach that makes no assumptions of the attacker. Through extensive numerical experiments with benchmark datasets, we show that the proposed defense mechanism outperforms the state of the art defenses in terms of prediction accuracy (up to 76% lower MSE compared to an undefended ridge model) and running time.

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。

↑