Language Technology Seminar Series (LaTeSS)

Towards Multilingual Evaluations of Knowledge for Large Language Models

Bryan Li, University of Pennsylvania
2-3pm Tue., Oct. 14, 2025, ITE 325b, UMBC

Get more information and register here.

This webinar is the first in the AI in Practice webinar series for the 2025-2026 academic year sponsored by the University of Baltimore, UMBC, and JHU.

AI Literacy: Employer Expectations for New College Graduates
Wednesday, October 8th | 12:00-1:00 PM EDT, online via Zoom

Register online: https://bit.ly/AiP-Oct8

What AI skills do employers actually want from new graduates? Join us as we go beyond the technical basics to explore the real-world competencies that drive hiring decisions today. Our expert panelists, Dean Merritt, Esq. from Mindgrub and Karolyn Babalola, PhD from Booz Allen Hamilton (UMBC '03), will share insights on essential AI literacy, ethical considerations, and the gap between classroom learning and workplace application. Perfect for students preparing for the job market, faculty designing curriculum, and career professionals staying ahead of industry trends.

Webinar video recording

The UMBC Cyber Defense Lab presents

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 EDT, Friday, October 3, 2025 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.

Recording of the event