Data clustering for the block profile method of intruder detection

The paper concerns the problem of computer security and intrusion detection. In particular the problem of detecting the masqueraders – intruders who pretend to be authorized users of computer systems. The article presents an improvement of the block profile method of intruder detection for computer systems. As a base for the work the block profiles were taken and the clustering of the block profiles data was performed. The aim was to detect the masqueraders within the test data. The problem of computer security is particularly important in medical applications. Activities of intruder can distort the data stored in medical databases and analyzed by the medical expert systems or decision support systems and thus make it difficult to support the diagnosis of diseases. For this reason it is necessary protect the medical computer systems from unauthorized access. This article presents the preliminary research and conclusions.