Paul Irofti

About me: 
 Resume (RO)
 Security Seminar


 Sisteme de Operare
 Utilizarea SO
 OS Security
 Vedere Artificială
 Static Analysis
 Prelucrarea Semnalelor
 Calcul Numeric

 [E-mail address]

Graphomaly – software package for anomaly detection in graphs modeling financial transactions





Team (University of Bucharest)

Paul Irofti -- Principal Investigator
Andrei Pătrașcu -- Senior Researcher
Andra Băltoiu -- Research Assistant

Coordinator Bogdan Dumitrescu (University Politehnica of Bucharest),
Industry Partener Ioan Cocan (Tremend).


[1] C. Rusu and P. Irofti, “Efficient and Parallel Separable Dictionary Learning,” in Proceedings of the IEEE 2021 27th International Conference on Parallel and Distributed Systems (ICPADS). 2021, pp. 1--6, IEEE Computer Society. [ bib | http ]
[2] A. Pătrașcu and P. Irofti, “Computational complexity of Inexact Proximal Point Algorithm for Convex Optimization under Holderian Growth,” pp. 1--42, 2021. [ bib | arXiv ]
[3] P. Irofti, L. Romero-Ben, F. Stoican, and V. Puig, “Data-driven Leak Localization in Water Distribution Networks via Dictionary Learning and Graph-based Interpolation,” 2021, pp. 1--6. [ bib | arXiv ]
[4] P. Irofti, C. Rusu, and A. Pătrașcu, “Dictionary Learning with Uniform Sparse Representations for Anomaly Detection,” 2021, pp. 1--6. [ bib | arXiv ]


Graphomaly Framework (source) (documentation) (pypi).

Python Dictionary Learning Toolbox (source) (documentation) (pypi).



The proposed project, called Graphomaly, aims to create a Python software package for anomaly detection in graphs that model financial transactions, with the purpose of discovering fraudulent behavior like money laundering, illegal networks, tax evasion, scams, etc. Such a toolbox is necessary in banks, where fraud detection departments still use mostly human experts.

The main tool that we propose is dictionary learning for sparse representations, which will be used to model sub-graphs derived from the full transactions graph through community detection. Other machine learning tools will be used for comparison, together with a set of data processing tools that are customary for dimensionality reduction.

There are two main working scenarios. In one, fraud patterns are known, but their shape can vary in size and also can be affected by other activities. In the other, unsupervised learning is used for the detection of anomalies, possibly of new types, that may be related to frauds.

The implemented methods will be able to process large graphs. Online and distributed forms of the algorithms will be derived, such that reaction time is decreased and thus frauds can be discovered in their incipient stages.

The consortium is made of two universities and a software firm and has the support of a bank that will provide relevant transactions data and will directly validate some of the results. The team members have relevant expertise in dictionary learning and related techniques, software architecture, data management and processing.