Daniela Brauckhoff
ETH Zurich
8 Papers
17 Citations
Daniela Brauckhoff is an academic researcher from ETH Zurich. The author has contributed to research in topics: Anomaly detection & Anomaly (physics). The author has an hindex of 6, co-authored 8 publications.
Chat about Author
Papers
Applying PCA for Traffic Anomaly Detection: Problems and Solutions
Daniela Brauckhoff,Kave Salamatian,Martin May +2 more
- 19 Apr 2009
TL;DR: A slightly modified version of PCA is developed that uses only data from a single router and proposes a solution to deal with the main problem, that PCA fails to capture temporal correlation, and is replaced with the Karhunen-Loeve transform.
Anomaly extraction in backbone networks using association rules
TL;DR: This paper uses meta-data provided by several histogram-based detectors to identify suspicious flows, and then applies association rule mining to find and summarize anomalous flows, which significantly reduces the work-hours needed for analyzing alarms, making anomaly detection systems more practical.
Automating root-cause analysis of network anomalies using frequent itemset mining
Ignasi Paredes-Oliva,Xenofontas Dimitropoulos,Maurizio Molina,Pere Barlet-Ros,Daniela Brauckhoff +4 more
- 30 Aug 2010
TL;DR: This work introduced a generic technique that uses frequent itemset mining to automatically extract and summarize the traffic flows causing an anomaly and showed that it works surprisingly well extracting the anomalous flows in most studied cases using sampled and unsampled NetFlow traces from two networks.
Comparison of anomaly signal quality in common detection metrics
Daniela Brauckhoff,Martin May,Bernhard Plattner +2 more
- 12 Jun 2007
TL;DR: This work presents ANEX (ANomaly EXposure), a simple and intuitive measure for comparing anomaly detection metrics regarding their capability to expose certain types of anomalies and illustrates the applicability of the measure by comparing 15 frequently-used detection metrics for the Blaster worm.
2
Automated Pattern-Based Service Deployment in Programmable Networks
TL;DR: A flexible service deployment architecture for the automated, on-demand deployment of distributed services in programmable networks by utilizing modular building blocks, namely navigation patterns, aggregation patterns, and capability functions, and the definition of a corresponding service descriptor.