Paul Irofti | Associate Professor

[PhotoID]

Associate Professor
The Research Center for Logic, Optimization and Security
Department of Computer Science
Faculty of Mathematics and Computer Science
University of Bucharest

Founding member and Vice-President
Institute for Logic and Data Science (ILDS)

I am interested in anomaly detection, dictionary learning, numerical analysis, signal processing, operating systems and security. I did my PhD in Systems Engineering in 2016 at the University Politehnica of Bucharest, under the supervision of Prof. Bogdan Dumitrescu.

Every Tuesday I am co-organizing the LOS research center seminar. The schedule and event details are here.

In the past I also organized every second Thursday the Cyber-security seminar (schedule and event details are here) that got suspended due to the recent pandemic. I am currently looking for co-organizers to help revive it.

Currently teaching the OS courses Operating System Security, Operating Systems, the mathematical machine learning courses Signal Processing and Numerical Recipies for Computer Science, and the formal methods security focused Static Analysis course.

In the past I also taught Using Operating Systems.

Researcher and Founding Member of
The Research Center for Logic, Optimization and Security (LOS)
University of Bucharest

NETALERT -- Automatic tools for detecting abnormal behavior in computer networks
SOL4 2021 project, September 2021 - May 2023

Goal: NetAlert aims to create a hardware-software sensor solution for detecting anomalies in computer networks based on the monitoring and analysis of data packets. The network-mounted sensor will provide real-time alerts on abnormal traffic behaviors using two complementary approaches:

(i) static analysis based on rules and behavioral patterns
(ii) machine learning (ML) analysis without prior expert knowledge

DDNET -- Data Driven Fault Accommodation for Distribution Networks
PD 2019 project, September 2020 - August 2022

Adapt and propose new dictionary learning methods for solving untractable fault detection and isolation problems found in distribution networks. Given a large dataset of sensor measurements from the distribution network, the dictionary learning algorithms should be able to produce the subset of network nodes where faults exist.

Graphomaly -- software package for anomaly detection in graphs modeling financial transactions
PED 2019 project, September 2020 - April 2022

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.

Founding member and Vice-President
Institute for Logic and Data Science (ILDS)

I am a founding member and vice-president of the Institute for Logic and Data Science. The institute is a non-profit independent research institute dedicated to the spread and advancement of logic-based and data-oriented scientific methods.

Founded in 2022 by five enthusiast scientists with experience in the academic and industrial worlds, ILDS is building a community of researchers and industry experts from Romania and abroad that work together on various research projects and share and advance their knowledge in scientific meetings.

Vice Dean (2020-2024)
Faculty of Mathematics and Computer Science
University of Bucharest

Vice Dean in charge of Research, IT, and Industry Relations.