Self-Defending Ledgers: Automating Distributed Ledger Security Using Multi-Agent Reinforcement Learning and Game Theory

Md Tariqul Islam 'Pavel'
Assistant Professor of Cybersecurity
UMBC Department of Information Systems

12–1pm ET, Wednesday, December 3, 2025
UMBC ITE 459 and online via Webex

Distributed ledger technologies (DLTs) continue to face significant security challenges. While attackers constantly adapt their strategies, governance mechanisms often remain static. Our work addresses this critical gap by introducing a framework for self-defending ledgers, where nodes enforce ledger security through adaptive governance driven by multi-agent reinforcement learning (MARL) grounded in game-theoretic principles. We model DLT consensus as a repeated Bayesian game, in which participants hold probabilistic beliefs about peer behavior, allowing agents to make strategic decisions under partial observability of adversarial actions. Our framework enables nodes to model, detect, and respond to a wide range of malicious behaviors, including bribery, selfish mining, equivocation, Sybil attacks, and collusive voting, by continuously updating Bayesian trust beliefs and governance policies based on network observations. We formally prove that networks with an honest majority reach stable equilibria and provide bounds on adversarial influence. Experiments across five major protocols show that agents effectively identify attacks with high accuracy while substantially reducing adversarial success. This work demonstrates the potential of game-theoretic MARL to provide robust, self-adaptive security in varied DLT environments, paving the way for resilient and autonomous ledger governance.

Md Tariqul Islam 'Pavel' is an assistant professor of cybersecurity in UMBC's Department of Information Systems. His research centers on the security, efficiency, and fault-tolerance of distributed computing systems, with a strong emphasis on blockchain, cloud, and vehicular networks. He develops formal models, algorithms, and protocols that address critical vulnerabilities in decentralized ecosystems, spanning inter-blockchain communication, smart contract migration, and trustworthy governance. His work combines cryptography, game theory, and system design to build scalable, resilient infrastructures. He earned his PhD and MS from the University of Kentucky and BS from the University of Dhaka, Bangladesh.

An Arabber Reunion and celebration supported by Baltimore Traces is in the news.

On Saturday, September 20, 2025 we held a celebration of Baltimore's arabber tradition and an arabber reunion–a day for arabbers past and present to come together and share their stories with the public. The event celebrated the 90th birthday of arabber Donald "China" Waugh and all those who have worked to keep the arabber tradition alive in Baltimore. For over a century, the arabbers of Baltimore have been more than just street vendors; they are a vital, living testament to the city's rich cultural tapestry and a powerful symbol of independent entrepreneurship.

Automate routine tasks and increase efficiency using Microsoft's generative AI tool

If your day is spent navigating the Microsoft 365 suite, Microsoft Copilot is a valuable AI resource built using OpenAI's large language model. Thanks to UMBC's enterprise license, the basic features of Microsoft Copilot Chat are available to all users free of charge, with information you type protected for Level 1 data. Once again, data at level 1 is considered non-public information. 

Common Use: Automating Administrative Tasks Copilot integrates directly into your Microsoft 365 environment, making it a critical tool for boosting productivity and saving time on routine, high-volume tasks.

The Storyline: Productivity Multiplier 

• Email Management: A staff member drowning in emails and reports can instantly turn their day around with Copilot. Instead of reading a lengthy thread, they can ask Copilot in Outlook to: "Summarize this long email thread from the Dean's office and list all the outstanding action items".

• Data Analysis (Staff): In Excel, a staff member can ask Copilot to "Analyze the student performance data in this sheet and create a pivot table showing enrollment trends by department over the last three semesters".

Resources:

• Try Copilot: The free version of Microsoft Copilot Chat is accessible on the web at copilot.microsoft.com on Windows, macOS, and iPadOS, though it has some limits during peak business hours.

• Premium Option: For heavy integration into Word, Excel, Teams, or Outlook, the Microsoft Copilot Pro license is available for purchase (approximately $336 a year).

• Cloud Development: UMBC's cloud computing contract with Microsoft Azure (Open AI) provides advanced options for generative AI development.

• Copilot Success Kit

• UMBC Gen AI FAQ

• UMBC Copilot FAQ

Name: Dharani Kousalya Penta

Pronouns: She/Her

Semester of Internship: Spring 2025

Major: Data Science

Current Class Level: Master's Student

This semester I completed a(n)...: Internship

Internship, Co-op, or Research Site (Company/Organization Name): Trulogik

Location of the Organization (City, State): Baltimore,Maryland

Title of position: Data Engineer Intern

Tell us about your internship, co-op, or research opportunity, including your day-to-day responsibilities:

During my Data Engineer internship at Trulogik, I supported the development of automated data workflows that improved operational visibility and reduced manual effort across the organization. My day-to-day responsibilities included writing SQL queries, cleaning and structuring data, and building Power BI dashboards that tracked real-time recruitment and operational KPIs. Early in the internship, I encountered challenges with inconsistent applicant-tracking data as we used different formats and naming conventions, which caused inaccuracies in the dashboards. I resolved this by creating standardized data models, implementing validation rules, and automating the entire pipeline so reports refreshed reliably without manual intervention. I also performed cohort analysis on sourcing channels to identify bottlenecks in the hiring funnel which helped leadership reallocate resources and improve conversion efficiency. Whenever pipelines broke due to schema changes or missing fields, I collaborated with team to debug the issue, adjust the logic, and ensure that dashboards reflected accurate, version-controlled data. Overall, this experience strengthened my skills in pipeline development, troubleshooting, and stakeholder communication and also foundational skills that directly prepare me for a full-time Data Engineer role.

Describe the process of obtaining your position. When did you hear of the position and submit your application?

I first learned about the internship opportunity at Trulogik during a career fair, where I visited them and explored the open positions they had posted for interns. After speaking with the team and gaining a better understanding of the role and the type of projects they were working on, I felt it aligned well with my interests. Shortly after the event, I reviewed the job description in detail and submitted my application along with my resume. This process allowed me to connect directly with the team, understand their expectations, and apply for the position in a timely manner.

What resources did you use to find your current experience?

UMBC Career Center, Career Fairs, Alumni Networking, Handshake, LinkedIn or other social media

What have you enjoyed the most about your position and organization?

What I enjoyed most about my position at Trulogik was the supportive and collaborative team environment. Everyone was willing to guide me, answer questions, and involve me in meaningful discussions about real-world data problems. This gave me the confidence to explore, experiment, and learn without hesitation. I also appreciated that I was trusted with real-time work rather than just observing. I was able to build dashboards, analyze data, and contribute to actual business decisions, which made the experience extremely rewarding. The combination of hands-on learning, mentorship, and exposure to real operational challenges not only strengthened my technical skills but also helped me understand how data engineering impacts day-to-day business operations.

How do you believe you have made an impact through your work?

I believe I made a meaningful impact through my work by improving the accuracy, efficiency, and clarity of the data that different teams relied on. My analysis of recruitment and sourcing channels gave leadership clearer visibility into where candidates were coming from and where bottlenecks existed, helping them make more informed decisions. I also helped resolve data inconsistencies and improve data quality, which directly strengthened reporting and decision-making across the organization. Overall, my contributions helped the team with better data, and with fewer errors creating value that continued even after my internship ended.

What advice would you give to another student who is seeking an internship or similar experience?

My biggest advice would be to actively build real, hands-on project experience whether through personal projects, class assignments, or open-source work. Being able to showcase practical skills makes a huge difference when applying. I would also recommend attending career fairs and networking events, because they provide direct access to employers and opportunities you might not find online. Additionally, connecting with UMBC alumni on LinkedIn or through campus events can be extremely valuable.Overall, stay proactive, keep learning independently, and don't hesitate to reach out to people.

Please provide a short reflection or quote about what you liked most about your position / earning internship credit / working with the Career Center.

What I enjoyed most about my position was the opportunity to work on real-world data problems with a team that was incredibly supportive and encouraging. The Career Center and especially Christine Routzahn played a major role in my journey. Her guidance, confidence-building, and advice were invaluable in helping me navigate the process and secure the internship.