Attack based on data:a novel perspective to attack sensitive points directly

扫码查看

原文链接

NETL
NSTL
万方数据

外文摘要：Adversarial attack for time-series classification model is widely explored and many attack methods are proposed.But there is not a method of attack based on the data itself.In this paper,we innovatively proposed a black-box sparse attack method based on data location.Our method directly attack the sensitive points in the time-series data accord-ing to statistical features extract from the dataset.At first,we have validated the transferability of sensitive points among DNNs with different structures.Secondly,we use the statistical features extract from the dataset and the sensi-tive rate of each point as the training set to train the predictive model.Then,predicting the sensitive rate of test set by predictive model.Finally,perturbing according to the sensitive rate.The attack is limited by constraining the L0 norm to achieve one-point attack.We conduct experiments on several datasets to validate the effectiveness of this method.

外文关键词：

Black-box adversarial attackTime series classificationData mining

作者：

Yuyao Ge、Zhongguo Yang、Lizhe Chen、Yiming Wang、Chengyang Li

展开 >

作者单位：

School of Information Science and Technology,North China University of Technology,Beijing,China

Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data,North China University of Technology,Beijing,China

School of Computer Science,Peking University,Beijing,China

基金：

Key Program of National Natural Science Foundation of ChinaInternational Cooperation and Exchange Program of National Natural Science Foundation of China

项目编号：

6183200462061136006

出版年：

2024

DOI：

10.1186/s42400-023-00179-4

网络空间安全科学与技术(英文版)

ISSN：

年,卷(期)：2024.7(3)