Anomaly Detection over Noisy Data using Learned Probability Distributions
ICML '00 Proceedings of the Seventeenth International Conference on Machine Learning
GATES: A Grid-Based Middleware for Processing Distributed Data Streams
HPDC '04 Proceedings of the 13th IEEE International Symposium on High Performance Distributed Computing
Supporting self-adaptation in streaming data mining applications
IPDPS'06 Proceedings of the 20th international conference on Parallel and distributed processing
| Hi-index | 0.00 |
Increasingly, a number of applications across computer sciences and other science and engineering disciplines rely on, or can potentially benefit from, analysis and monitoring of data streams. We view the problem of flexible and adaptive processing of distributed data streams as a grid computing problem. In our recent work, we have been developing a middleware, GATES (Grid-based AdapTive Execution on Streams), for enabling grid-based processing of distributed data streams. This paper reports an application study using the GATES middleware system. We focus on the problem of intrusion detection. We have created a distributed and self-adaptive real-time implementation of the algorithm proposed by Eskin using our middleware. The main observations from our experiments are as follows. First, our distributed implementation can achieve detection rates which are very close to the detection rate by a centralized algorithm. Second, our implementation is able to effectively adjust the adaptation parameters.