Darius Mihai
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Darius Mihai has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
- Maria-Elena Mihailescu
Faculty of Automatic Control and Computers, National University of Science and Technology POLITEHNICA Bucharest, 060042 Bucharest, Romania
4 shared publications - Mihai Carabas
Universitatea Nationala de Stiinta si Tehnologie Politehnica Bucuresti
3 shared publications - Mihai Dascalu
Computer Science & Engineering Department, National University of Science and Technology POLITEHNICA Bucharest, 313 Splaiul Independentei, 060042 Bucharest, Romania
2 shared publications - Alexandru Dima
Faculty of Automatic Control and Computers, National University of Science and Technology POLITEHNICA Bucharest, 060042 Bucharest, Romania
1 shared publication Andreea Dutulescu
National University of Science and Technology Politehnica Bucharest
1 shared publicationAndrei Brebene
Politehnica University of Bucharest,Bucharest,Romania
1 shared publication
Latest Publications
- Open Access
FroLineR: Front-Line Response with Retrieval-Augmented Prompt-Engineered Reply Generation for IT Help Desks
IT help desks at large organizations face a high volume of recurrent, well-documented user requests that nevertheless require human-written replies, creating a persistent staff workload that is repetitive in content but non-trivial in tone and procedural correctness. We present FroLineR, short for Front-Line Response, a system that drafts the initial staff reply to such tickets in the login and account-activation category and integrates into a human-in-the-loop ticketing workflow on a Romanian-language ticketing platform. The generator is an unmodified instruct model augmented with retrieval from a small set of hand-curated guide documents, using a Romanian system prompt refined over several rounds of staff review. To evaluate and refine the prompt without manual labeling, we cluster the first user message of every historical thread with both BERTopic and Semantic Signal Separation (), score configurations along coherence and lexical-diversity axes, and extract a 200-message evaluation set from the winning model. Prompt convergence was certified by several rounds of manual review by support staff. The production system is quantized to Q4_K_M GGUF, served through llama-cpp-python behind a small Flask API, and deployed with GPU offloading on the target server, reducing end-to-end per-answer latency from approximately 830 s on the server’s CPU to roughly 61 s once layers are offloaded to the GPU, with no observable degradation in answer quality.Open AccessFroLineR: Front-Line Response with Retrieval-Augmented Prompt-Engineered Reply Generation for IT Help Desks
IT help desks at large organizations face a high volume of recurrent, well-documented user requests that nevertheless require human-written replies, creating a persistent staff workload that is repetitive in content but non-trivial in tone and procedural correctness. We present FroLineR, short for Front-Line Response, a system that drafts the initial staff reply to such tickets in the login and account-activation category and integrates into a human-in-the-loop ticketing workflow on a Romanian-language ticketing platform. The generator is an unmodified instruct model augmented with retrieval from a small set of hand-curated guide documents, using a Romanian system prompt refined over several rounds of staff review. To evaluate and refine the prompt without manual labeling, we cluster the first user message of every historical thread with both BERTopic and Semantic Signal Separation (), score configurations along coherence and lexical-diversity axes, and extract a 200-message evaluation set from the winning model. Prompt convergence was certified by several rounds of manual review by support staff. The production system is quantized to Q4_K_M GGUF, served through llama-cpp-python behind a small Flask API, and deployed with GPU offloading on the target server, reducing end-to-end per-answer latency from approximately 830 s on the server’s CPU to roughly 61 s once layers are offloaded to the GPU, with no observable degradation in answer quality. - Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 134401-134418
From Cybersecurity News to Vulnerability Records: Neural Information Extraction for Vulnerability Tracking
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 134401-134418
Open AccessFrom Cybersecurity News to Vulnerability Records: Neural Information Extraction for Vulnerability Tracking
- 21 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Automated Infrastructure Provisioning
The paper is focused on developing an automated infrastructure provisioning that simplifies the process of setting up and managing a network of virtual machines. The infrastructure will utilize virtualization technologies to create a cluster of machines that can be quickly and easily configured to meet the needs of the user. The system will also provide tools for managing the machines and their associated resources.
- 21 September 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-5
Automated Infrastructure Provisioning
The paper is focused on developing an automated infrastructure provisioning that simplifies the process of setting up and managing a network of virtual machines. The infrastructure will utilize virtualization technologies to create a cluster of machines that can be quickly and easily configured to meet the needs of the user. The system will also provide tools for managing the machines and their associated resources.
- Open Access
- 23 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 8441-8454
Integrated High-Workload Services for E-Learning
E-learning platforms are valuable tools to support and enhance the learning and teaching process during online classes. Even though these platforms are already well-known and have been widely used for a long time, transitioning to fully online activities with a large number of users can lead to an exponential growth in resource usage. Moreover, the availability of these platforms becomes critical since the learning activities cannot be interrupted, and the vital information (assignments, grades, and shared resources) cannot be lost. Thus, the system administrators must implement a scalable solution to accommodate many users and activities. Determining the most suitable architecture is a non-trivial task that must consider the various tools, services, and interconnect options that are available. This paper presents our approach to setting up an integrated high-workload e-learning setup used for online classes in University Politehnica of Bucharest and can be used as a reference by other universities.
- 23 January 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 8441-8454
Open AccessIntegrated High-Workload Services for E-Learning
E-learning platforms are valuable tools to support and enhance the learning and teaching process during online classes. Even though these platforms are already well-known and have been widely used for a long time, transitioning to fully online activities with a large number of users can lead to an exponential growth in resource usage. Moreover, the availability of these platforms becomes critical since the learning activities cannot be interrupted, and the vital information (assignments, grades, and shared resources) cannot be lost. Thus, the system administrators must implement a scalable solution to accommodate many users and activities. Determining the most suitable architecture is a non-trivial task that must consider the various tools, services, and interconnect options that are available. This paper presents our approach to setting up an integrated high-workload e-learning setup used for online classes in University Politehnica of Bucharest and can be used as a reference by other universities.
- Open Access
The Proposition and Evaluation of the RoEduNet-SIMARGL2021 Network Intrusion Detection Dataset
Cybersecurity is an arms race, with both the security and the adversaries attempting to outsmart one another, coming up with new attacks, new ways to defend against those attacks, and again with new ways to circumvent those defences. This situation creates a constant need for novel, realistic cybersecurity datasets. This paper introduces the effects of using machine-learning-based intrusion detection methods in network traffic coming from a real-life architecture. The main contribution of this work is a dataset coming from a real-world, academic network. Real-life traffic was collected and, after performing a series of attacks, a dataset was assembled. The dataset contains 44 network features and an unbalanced distribution of classes. In this work, the capability of the dataset for formulating machine-learning-based models was experimentally evaluated. To investigate the stability of the obtained models, cross-validation was performed, and an array of detection metrics were reported. The gathered dataset is part of an effort to bring security against novel cyberthreats and was completed in the SIMARGL project.
Open AccessThe Proposition and Evaluation of the RoEduNet-SIMARGL2021 Network Intrusion Detection Dataset
Cybersecurity is an arms race, with both the security and the adversaries attempting to outsmart one another, coming up with new attacks, new ways to defend against those attacks, and again with new ways to circumvent those defences. This situation creates a constant need for novel, realistic cybersecurity datasets. This paper introduces the effects of using machine-learning-based intrusion detection methods in network traffic coming from a real-life architecture. The main contribution of this work is a dataset coming from a real-world, academic network. Real-life traffic was collected and, after performing a series of attacks, a dataset was assembled. The dataset contains 44 network features and an unbalanced distribution of classes. In this work, the capability of the dataset for formulating machine-learning-based models was experimentally evaluated. To investigate the stability of the obtained models, cross-validation was performed, and an array of detection metrics were reported. The gathered dataset is part of an effort to bring security against novel cyberthreats and was completed in the SIMARGL project.