Developing machine learning methods for network anomaly detection
Özet
Machine learning refers to training of a computer (machine) to be able to acquire knowledge from data (i.e. experience) and improve itself on a given task. The field of machine learning has become a mainstream, improving hundreds of millions of lives. Fraudulent actions in computer networks, credit card transactions and website advertisement traffic might devastate large businesses and cause anually fiscal loss of billions of dollars around the globe. In this thesis, we propose various machine learning methods for three fraud detection problems: network anomaly detection, credit card fraud detection and detection of fraudulent clicks to advertisements on the internet. We design various classifiers such as logistic regression, k-nearest neighbors, decision tree, support vector machine, and ensemble classifiers such as random forest, bagging, stacking and AdaBoost. The hyper-parameters of the classifiers are optimized by performing cross-validation experiments on train sets. In the next step, the models are trained using the optimum hyper-parameter configurations and predictions are computed on test sets. Among the various methods compared the highest accuracy is obtained by ensemble learners.
Koleksiyonlar
İlgili Öğeler
Başlık, yazar, küratör ve konuya göre gösterilen ilgili öğeler.
-
A deep learning approach with Bayesian optimization and ensemble classifiers for detecting denial of service attacks
Gormez, Yasin; Aydin, Zafer; Karademir, Ramazan; Gungor, Vehbi C. (WILEY, 111 RIVER ST, HOBOKEN 07030-5774, NJ USA, 2020)Detecting malicious behavior is important for preventing security threats in a computer network. Denial of Service (DoS) is among the popular cyber attacks targeted at web sites of high-profile organizations and can ... -
Machine learning algorithms against hacking attack and detection success comparison
Yavuz L.; Soran A.; Onen A.; Muyeen S.M. (Institute of Electrical and Electronics Engineers Inc., 2020)Power system protection units has got enormous importance with the growing risk of cyber-attacks. To create sustainable and well protected system, power system data must be healthy. For that purpose, many machine learning ... -
A Simple Method for Enhancing the SNR in Direct Detection (p-OTDR based Distributed Acoustic Sensors
Uyar, Faruk; Kartaloglu, Tolga; Unal, Canberk; Ozbay, Ekmel; Ozdur, Ibrahim (IEEE, 345 E 47TH ST, NEW YORK, NY 10017 USA, 2020)A simple and effective method for increasing the SNR and range in fp-OTDR based direct -detection distributed acoustic sensors is proposed and experimentally verified. The proposed method results in 11 dB SNR improvement ...