A misleading attack against semi-supervised learning for intrusion detection

Authors:
Fangzhou Zhu;Jun Long;Wentao Zhao;Zhiping Cai
Affiliations:
Huazhong University of Science and Technology, Wuhan, China and National University of Defense Technology, Changsha, Hunan, China;Huazhong University of Science and Technology, Wuhan, China and National University of Defense Technology, Changsha, Hunan, China;Huazhong University of Science and Technology, Wuhan, China and National University of Defense Technology, Changsha, Hunan, China;Huazhong University of Science and Technology, Wuhan, China and National University of Defense Technology, Changsha, Hunan, China
Venue:
MDAI'10 Proceedings of the 7th international conference on Modeling decisions for artificial intelligence
Year:
2010

Citing 16
Cited 0

Text Classification from Labeled and Unlabeled Documents using EM

Machine Learning - Special issue on information retrieval
A framework for constructing features and models for intrusion detection systems

ACM Transactions on Information and System Security (TISSEC)
Transductive Inference for Text Classification using Support Vector Machines

ICML '99 Proceedings of the Sixteenth International Conference on Machine Learning
Learning nonstationary models of normal network traffic for detecting novel attacks

Proceedings of the eighth ACM SIGKDD international conference on Knowledge discovery and data mining
Unsupervised word sense disambiguation rivaling supervised methods

ACL '95 Proceedings of the 33rd annual meeting on Association for Computational Linguistics
Adversarial learning

Proceedings of the eleventh ACM SIGKDD international conference on Knowledge discovery in data mining
Can machine learning be secure?

ASIACCS '06 Proceedings of the 2006 ACM Symposium on Information, computer and communications security
Machine learning in intrusion detection

Machine learning in intrusion detection
Evading network anomaly detection systems: formal reasoning and practical techniques

Proceedings of the 13th ACM conference on Computer and communications security
Manifold Regularization: A Geometric Framework for Learning from Labeled and Unlabeled Examples

The Journal of Machine Learning Research
Collaborative Intrusion Prevention

WETICE '07 Proceedings of the 16th IEEE International Workshops on Enabling Technologies: Infrastructure for Collaborative Enterprises
Semi-supervised co-training and active learning based approach for multi-view intrusion detection

Proceedings of the 2009 ACM symposium on Applied Computing
Introduction to Semi-Supervised Learning

Introduction to Semi-Supervised Learning
Undermining an anomaly-based intrusion detection system using common exploits

RAID'02 Proceedings of the 5th international conference on Recent advances in intrusion detection
Learning classifiers for misuse detection using a bag of system calls representation

ISI'05 Proceedings of the 2005 IEEE international conference on Intelligence and Security Informatics
Paragraph: thwarting signature learning by training maliciously

RAID'06 Proceedings of the 9th international conference on Recent Advances in Intrusion Detection

Quantified Score

Hi-index	0.00

Visualization

Abstract

Machine learning has became a popular method for intrusion detection due to self-adaption for changing situation. Limited to lack of high quality labeled instances, some researchers focused on semi-supervised learning to utilize unlabeled instances enhancing classification. But involving the unlabeled instances into learning process also introduces vulnerability: attackers can generate fake unlabeled instances to mislead the final classifier so that a few intrusions can not be detected. We show how attackers can influence the semi-supervised classifier by constructing unlabeled instances in this paper. And a possible defence method which based on active learning is proposed. Experiments show that the misleading attack can reduce the accuracy of the semi-supervised learning method and the presented defense method against the misleading attack can obtain higher accuracy than the original semi-supervised learner under the proposed attack.