A Universal Approach for Anomaly Detection in Log Files
| Název práce v češtině: | Univerzální přístup pro odhalování anomálií v logovacích souborech |
|---|---|
| Název v anglickém jazyce: | A Universal Approach for Anomaly Detection in Log Files |
| Klíčová slova: | detekce anomálií|log|topologie sítě|strojové učení |
| Klíčová slova anglicky: | anomaly detection|log|network topology|machine learning |
| Akademický rok vypsání: | 2022/2023 |
| Typ práce: | diplomová práce |
| Jazyk práce: | angličtina |
| Ústav: | Katedra softwarového inženýrství (32-KSI) |
| Vedoucí / školitel: | Ing. Pavel Koupil, Ph.D. |
| Řešitel: | Mgr. Radovan Tomala - zadáno a potvrzeno stud. odd. |
| Datum přihlášení: | 01.09.2022 |
| Datum zadání: | 01.09.2022 |
| Datum potvrzení stud. oddělením: | 06.12.2022 |
| Datum a čas obhajoby: | 12.06.2023 09:00 |
| Datum odevzdání elektronické podoby: | 04.05.2023 |
| Datum odevzdání tištěné podoby: | 09.05.2023 |
| Datum proběhlé obhajoby: | 12.06.2023 |
| Oponenti: | doc. Mgr. Martin Pilát, Ph.D. |
| Zásady pro vypracování |
| There exist a variety of methods to find abnormalities in datasets, whether based on expert models, AI rules, genetic algorithms, etc. However, these solutions are often customized to a particular problem and the general applicability is very limited. A challenging problem is to identify a method that will be suitable for a specific problem. Moreover, if a candidate method is found, it still has to be tuned to the specific problem.
The author first performs an analysis and comparison of selected existing methods, e.g., over one or two selected datasets. Based on this, he/she proposes a set of rules to guide the selection of a suitable method to address a particular problem. Finally, the author will implement a prototype that will experimentally validate the set of rules on one or two selected problems. |
| Seznam odborné literatury |
| CHANDOLA, Varun; BANERJEE, Arindam; KUMAR, Vipin. Anomaly detection: A survey. ACM computing surveys (CSUR), 2009, 41.3: 1-58.
AHMED, Mohiuddin; MAHMOOD, Abdun Naser; HU, Jiankun. A survey of network anomaly detection techniques. Journal of Network and Computer Applications, 2016, 60: 19-31. BHUYAN, Monowar H.; BHATTACHARYYA, Dhruba Kumar; KALITA, Jugal K. Network anomaly detection: methods, systems and tools. Ieee communications surveys & tutorials, 2013, 16.1: 303-336. PANG, Guansong, et al. Deep learning for anomaly detection: A review. ACM Computing Surveys (CSUR), 2021, 54.2: 1-38. ZENATI, Houssam, et al. Adversarially learned anomaly detection. In: 2018 IEEE International conference on data mining (ICDM). IEEE, 2018. p. 727-736. CHALAPATHY, Raghavendra; CHAWLA, Sanjay. Deep learning for anomaly detection: A survey. arXiv preprint arXiv:1901.03407, 2019. MEHROTRA, Kishan G.; MOHAN, Chilukuri K.; HUANG, HuaMing. Anomaly detection principles and algorithms. New York, NY, USA:: Springer International Publishing, 2017. |