A probabilistic approach to fraud detection in telecommunications

Olszewski, Dominik

doi:10.1016/j.knosys.2011.08.018

Cited by 59 publications

(23 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A practical problem is the selection of the parameters in the model which should be addressed in the future. Furthermore, practical applications (such as [36][37][38][39][40]) are also interesting.…”

Section: Discussionmentioning

confidence: 99%

Probabilistic outputs for twin support vector machines

Shao

Deng

Yang

et al. 2012

Knowledge-Based Systems

View full text Add to dashboard Cite

Section: Discussionmentioning

confidence: 99%

Probabilistic outputs for twin support vector machines

Shao

Deng

Yang

et al. 2012

Knowledge-Based Systems

View full text Add to dashboard Cite

“…Yusoff [16] proposed an approach using Gaussian mixed model (GMM), a probabilistic model which can not only be successfully applied to speech recognition problems but also fraud detection problems. Based on LDA, [9] detects the fraud using a threshold-type classification algorithm. Cahill et al [3] built an adaptive fraud detection framework [5] which used an event-driven approach that assigns fraud scores to detect fraud as it happens, and weighted recent mobile phone calls more heavily than earlier ones.…”

Section: Related Workmentioning

confidence: 99%

PFrauDetector: A Parallelized Graph Mining Approach for Efficient Fraudulent Phone Call Detection

Ying

Huang

et al. 2016

2016 IEEE 22nd International Conference on Parallel and Distributed Systems (ICPADS)

View full text Add to dashboard Cite

Abstract-In recent years, fraud is becoming more rampant internationally with the development of modern technology and global communication. Due to the rapid growth in the volume of call logs, the task of fraudulent phone call detection is confronted with Big Data issues in real-world implementations. While our previous work, FrauDetector, has addressed this problem and achieved some promising results, it can be further enhanced as it focuses on the fraud detection accuracy while the efficiency and scalability are not on the top priority. Meanwhile, other known approaches suffer from long training time and/or cannot accurately detect fraudulent phone calls in real time. In this paper, we propose a highly-efficient parallelized graph-miningbased fraudulent phone call detection framework, namely PFrauDetector, which is able to automatically label fraudulent phone numbers with a "fraud" tag, a crucial prerequisite for distinguishing fraudulent phone call numbers from the normal ones. PFrauDetector generates smaller, more manageable subnetworks from the original graph and performs a parallelized weighted HITS algorithm for significant speed acceleration in the graph learning module. It adopts a novel aggregation approach to generate the trust (or experience) value for each phone number (or user) based on their respective local values. We conduct a comprehensive experimental study based on a real dataset collected through an anti-fraud mobile application, Whoscall. The results demonstrate a significantly improved efficiency of our approach compared to FrauDetector and superior performance against other major classifier-based methods.

show abstract

“…There have been numerous attempts to detect intrusions in computer systems Kudłacik 2013, 2014) and networks (Fiore et al 2013;Palmieri and Fiore 2010;Palmieri et al 2014;Salem et al 2008;Wang et al 2008) or frauds in telecommunication (Olszewski 2012) as it has also become an important part of human life.…”

Section: Related Work and Critical Remarksmentioning

confidence: 99%

Fuzzy approach for intrusion detection based on user’s commands

2015

View full text Add to dashboard Cite

The article concerns the problem of detecting masqueraders in computer systems. A masquerader in a computer system is an intruder who pretends to be a legitimate user in order to gain access to protected resources. The article presents an intrusion detection method based on a fuzzy approach. Two types of user's activity profiles are proposed along with the corresponding data structures. The solution analyzes the activity of the computer user in a relatively short period of time, building a user's profile. The profile is based on the most recent activity of the user, therefore, it is named the local profile. Further analysis involves creating a more general structure based on a defined number of local profiles of one user, called the fuzzy profile. It represents a generalized behavior of the computer system user. The fuzzy profiles are used directly to detect abnormalities in users' behavior, and thus possible intrusions. The proposed solution is prepared to be able to create user's profiles based on any countable features derived from user's actions in computer system (i.e., used commands, mouse and keyboard data, requested network resources). The presented method was tested using one of the commonly available standard intrusion data sets containing command names executed by users of a Unix system. Therefore, the obtained results can be compared with other approaches. The results of the experiments Communicated by V. Loia. have shown that the method presented in this article is comparable with the best intrusion detection methods, tested with the same data set, in the matter of the obtained results. The proposed solution is characterized by a very low computational complexity, which has been confirmed by experimental results.

show abstract

A probabilistic approach to fraud detection in telecommunications

Cited by 59 publications

References 16 publications

Probabilistic outputs for twin support vector machines

Probabilistic outputs for twin support vector machines

PFrauDetector: A Parallelized Graph Mining Approach for Efficient Fraudulent Phone Call Detection

Fuzzy approach for intrusion detection based on user’s commands

Contact Info

Product

Resources

About