An example-based mapping method for text categorization and retrieval
ACM Transactions on Information Systems (TOIS)
Naive (Bayes) at Forty: The Independence Assumption in Information Retrieval
ECML '98 Proceedings of the 10th European Conference on Machine Learning
Data mining approaches for intrusion detection
SSYM'98 Proceedings of the 7th conference on USENIX Security Symposium - Volume 7
A study on optimal parameter tuning for Rocchio text classifier
ECIR'03 Proceedings of the 25th European conference on IR research
Hi-index | 0.00 |
Security in telemedicine systems might be considered a particularly sensitive subject due to the type of confidential information generally handled and the responsibilities consequently derived. In this work we focus on detecting attempts of gaining unauthorised access to a telemedicine web application. We introduce a new Text Mining module that by using Text Categorisation of the web application server log entries is capable of learning the characteristics of both normal and malicious user behaviour. As a result, the detection of misuse in the web application is achieved without the need of explicit programming hence improving the system maintainability.