About
Cybersecurity & AI.
I am a cybersecurity researcher with a deep interest in the next generation (nextG) of wireless networks. Specifically, my research focuses on cybersecurity within the context of 5G and nextG, where I explore vulnerabilities and mitigation strategies in the Open Radio Access Network (ORAN). Additionally, I specialize in the intersection of adversarial machine learning and cybersecurity. My previous studies have centered on identifying vulnerabilities in human behavior. Furthermore, I have substantial industry experience as a Systems Analyst. I am dedicated to advancing the field through rigorous academic pursuits and innovative approaches.
- Degree: Master of Science/ PhD student
- E-mail: jeffersonva@vt.edu
- City: Arlington, VA, 🇺🇸
Resume
Sumary
Jefferson Viana
Cybersecurity researcher passionate about next-gen wireless networks (5G/nextG). Expertise in ORAN vulnerabilities and mitigation strategies, with focus on adversarial machine learning. Also a experienced Systems Analyst. Committed to advancing the state-of-the-art through academic rigor and innovation.
- jeffersonva@vt.edu
Education
Master of Science: Mobile Networks
2022 - Present
Virginia Tech, Arlington, VA 🇺🇸
The rapid growth of mobile network traffic and the densification required for 6G networks significantly increase energy consumption, with base stations (BS) accounting for up to 70\% of total network energy use. Energy-efficient BS switching has therefore become a critical research focus. Traditional solutions rely on static thresholds or fixed cost function weights, limiting adaptability in dynamic environments. This thesis investigates how cost function design and weight adaptation influence the trade-off between energy consumption and Quality of Service (QoS) degradation in Deep Reinforcement Learning (DRL)-based BS switching. Using a realistic spatio-temporal dataset, we show that static cost weights lead to suboptimal performance under varying traffic conditions. To address this, we propose a Hierarchical Reinforcement Learning (HRL) architecture in which a high-level controller dynamically selects low-level policies trained with different cost function weights. Experimental results demonstrate that the proposed HRL approach achieves up to 64\% energy reduction—improving by 5% over the static DRL baseline—while maintaining acceptable QoS levels. These findings highlight the potential of hierarchical control and adaptive weighting in achieving scalable, sustainable 6G Radio Access Networks operations.
Master of Science: Informatics (Cybersecurity and AI)
2019 - 2021
University of Brasília, Brasília, BR 🇧🇷
Online social networks like Twitter provide a novel channel to allow interaction between human beings. However, its success has attracted interest in attacking and exploiting through a wide range of unethical activities, such as malicious actions to manipulate users. One of the methods to carry out these abuses is the use of bots on Twitter. Such behavior needs investigation aiming to mitigate its effects. Recently, machine learning (ML) classifiers to distinguish between real and bot accounts have proven advances. In this work, we explored the technique by constructing a multi-agent system (MAS) capable of performing the Twitter bot detection autonomously. It is based on supervised classification with three ML algorithms and a reduced set of features. When tested offline, this MAS achieved good performance with an average of AUC equal to 0.9856 and a standard deviation of 0.0199. Using it for online bot detection on a Proof of Concept results suggest that 88.19\% of bots detected were correctly labeled. On a comprehensive experiment, more than 780 thousand tweets were captured during five days. 1,597 tweets were from profiles classified as bots (678 unique profiles), indicating that the approach used is feasible and practical for the real-time bot detection problem.
Bachelor of Science: Computer Science
2013 - 2018
University of Brasília, Brasília, BR 🇧🇷
The undergraduate thesis is about the development of a mathematical-computational model to detect Twitter accounts that may be vulnerable to phishing attacks. Through descriptive, exploratory, and quantitative research based on a series of experiments, it verifies the existence of correlations between some attributes of Twitter accounts and the vulnerability of their users to phishing attacks. I executed four different incremental versions of experiments. These experiments performed fake phishing attacks directed to approximately 1287 Twitter accounts extended across 38 days. My results were analyzed through logistic regression. The regression confirmed that it's possible to create 'victim profiles' based on account attributes, making it possible to execute phishing attacks with precision better than a random choice. Moreover, it is possible to build and run a tool that executes automated social engineering attacks.
Professional Experience
Graduate Research Assistant
2022 - Present
Commonwealth Cyber Initiative (CCI), Arlington, VA 🇺🇸
- Execution of research on cutting-edge mobile networks.
Front-end Systems Analyst
2019 - 2022
Stefanini IT Solutions, Brasília, DF 🇧🇷
- Analysis and development of front-end systems. Outsourced for the Bank of Brazil.
Tutor
2018 - 2018
Introduction to Computer Science (University of Brasília), Brasília, DF 🇧🇷
- Give practical classes to begginer students.
RAD Software Developer (Intern)
2016 - 2018
Federal General Accounting Office (TCU), Brasília, DF 🇧🇷
- Development and maintenance decentralized internsystems using Oracle Apex, and support to the auditors with DB queries.
Teacher Assistantship
2015 - 2015
Introduction to information systems (University of Brasília), Brasília, DF 🇧🇷
- Assistantship to the professor with practical classes, and correction of another students projects.
Teacher Assistantship
2014 - 2014
Data structures (University of Brasília), Brasília, DF 🇧🇷
- Assistantship to the professor with practical classes, and correction of another students projects.
Teacher Assistantship
2013 - 2013
Basic computing (University of Brasília), Brasília, DF 🇧🇷
- Assistantship to the professor with practical classes, and correction of another students projects.