.png){kind=icon}
返回
Sparse Feature Attacks in Adversarial Learning
.png){kind=icon}
PRE
AI
DOI：10.1109/TKDE.2018.2790928.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Adversarial learning is the study of machine learning techniques deployed in non-benign environments. Example applications include classification for detecting spam, network intrusion detection, and credit card scoring. In fact, as the use of machine learning grows in diverse application domains, the possibility for adversarial behavior is likely to increase. When adversarial learning is modelled in a game-theoretic setup, the standard assumption about the adversary (player) behavior is the ability to change all features of the classifiers (the opponent player) at will. The adversary pays a cost proportional to the size of the attack. We refer to this form of adversarial behavior as a dense feature attack. However, the aim of an adversary is not just to subvert a classifier but carry out data transformation in a way such that spam continues to remain effective. We demonstrate that an adversary could potentially achieve this objective by carrying out a sparse feature attack. We design an algorithm to show how a classifier should be designed to be robust against sparse adversarial attacks. Our main insight is that sparse feature attacks are best defended by designing classifiers which use l(1) regularizers.
Keyword:
Adversarial learning
sparse modelling
l(1) regularizer
stackelberg game
nash equilibrium
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
10.4
论文数:
6.8K
被引数:
3.2W
机构
引用论文
.png){kind=icon}
Graph Regularized Non-Negative Low-Rank Matrix Factorization for Image Clustering用于图像聚类的图正则化非负低秩矩阵分解
PREAI
分享收藏
查看更多内容