Secure Machine Learning, a Brief Overview
Authors:
- Xiaofeng LiaoXLXiaofeng Liao
- Liping DingLDLiping Ding
- Yongji WangYWYongji Wang
- 1 June 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 26-29
Abstract
The purpose of this article is to give a brief overview on the current work towards the emerging research problem of secure machine learning. Machine learning technique has been applied widely in various applications especially in spam detection and network intrusion detection. Most existing learning schemes assume that the environment they settle in is benign. However this is not always true in the real adversarial decision-making situations where the future data sets and the training data set are no longer from the same population, due to the transformations employed by the adversaries. As more and more machine learning systems are put into use, it is imperative to consider the security of the machine learning system. As a emerging problem, it is attracting more and more researchers' attention. In this article, we present a brief overview on secure machine learning and current progress on developing secure machine learning algorithms.Keywords
This publication has 17 references indexed in Scilit:
- Classifier evaluation and attribute selection against active adversariesData Mining and Knowledge Discovery, 2010
- Mining adversarial patterns via regularized loss minimizationMachine Learning, 2010
- The security of machine learningMachine Learning, 2010
- Intrusion detection by machine learning: A reviewExpert Systems with Applications, 2009
- Advanced Allergy Attacks: Does a Corpus Really Help?2007
- Can machine learning be secure?2006
- Adversarial learning2005
- Shilling recommender systems for fun and profit2004
- Using Trust in Recommender Systems: An Experimental Analysis2004
- Undermining an Anomaly-Based Intrusion Detection System Using Common Exploits2002