Congratulations Dave Souder and Khalil Alston for being selected as this month’s DoIT Gritty Award winner!

We are proud to announce that Dave Souder and Khalil Alston have been awarded the DoIT Gritty Award for their critical support of National STEM Day.  

Dave and Khalil designed the hybrid event to meet the needs of sponsors and presenters, trained all of the presenters, and provided day-of event support. The event was a STEM Speed Networking Event, held as a webinar. At least 45 students who registered through the Career Center attended this event and 15 professionals from the Environmental Protection Agency, United States Geological Survey (USGS), and United States Forest Service shared information about career paths and internships with students.

A few weeks before the event, Dave and Khalil were brought in to assist with the National STEM Day virtual event taking place on Friday, November 8th. With the assistance of Audio Visual full-time staff Steve Anderson, Hunter Gordon, and a team of DoIT student employees, they started testing the Webex Webinar process and workflow. They set up several test meetings internally and then, as we received the list of external presenters, Khalil and Dave started meeting individually over Webex with them to be sure they could all attend and present smoothly on the day of the event. 

They worked closely with members of the Office of the Provost, the UMBC Career Center, USGS, and the Chesapeake Bay Program to put this program together as a team effort. They are looking to expand this event to include other Universities and Government Agencies in the future, as it was a wonderful networking opportunity for the students and panelists who attended. 

For their exceptional efforts and commitment to excellence, we are proud to present Dave and Khalil with the DoIT Gritty Award. Congratulations!

The Gritty Award is in recognition of outstanding work within the Division. Full-time DoIT employees and teams are eligible to be nominated for going above and beyond! Anyone in DoIT can nominate someone for the Gritty by completing this short Gritty Nomination Form. 

Thank you for all of your hard work, Khalil and Dave! 

The DoIT Community & The DoIT Gritty Committee

Erica D’Eramo

Ally Hepp

Carlos McKinney

David Toothe

Dondre Hatef

Kashka Donaldson

Mariann Hawken

Nick Beech

Tony Finneran

Roy Prouty

The Talent Learning & Organizational Development team needs YOU! As our team continues to develop and enhance our learning and development offerings for the campus, it is critical that we stay connected to the pulse and this is where you come in! As we understand your motivation, challenges, and desires, we can all help shape the future of professional development and continue UMBC’s legacy as a Great College to Work For!

To enable focused conversation, we have created 4 separate virtual focus group sessions for different populations:

Faculty - February 14th from 9:00 a.m. - 11:00 a.m.

New Hires - February 18th from 9:00 a.m. - 11:00 a.m. (new date)

Staff - February 24th from 10:30 a.m. - 12:30 p.m.

Manager/Leader - February 26th from 1:30 p.m. - 3:30 p.m.

You may sign up for your chosen session here! Please hold your calendar and stay tuned for a webex link. 

Securing Distributed Networks: Leveraging Reinforcement Learning and Game Theory for Attack Detection and Mitigation

Dr. Md Tariqul Islam, Syracuse University

10-11am January 30, 2025;  ITE 459, UMBC and online

Reinforcement learning (RL) has demonstrated remarkable success across diverse domains, from mastering complex games to optimizing real-time feedback systems in robotics and industrial control. However, its potential in cybersecurity, particularly for autonomous attack detection and mitigation in distributed systems, remains largely underexplored. Traditional single-agent RL approaches struggle in decentralized environments where multiple entities make independent decisions, necessitating multi-agent reinforcement learning (MARL). Our research explores blockchain networks as an ideal test case due to their decentralized architecture and trustless consensus mechanisms. We developed a novel MARL-based consensus mechanism for Proof-of-Stake blockchains, enabling nodes to collaboratively identify and penalize malicious behavior while preserving decentralization. This approach effectively mitigated six major blockchain attack types with minimal computational overhead. Building on these results, we propose integrating game-theoretic principles into the MARL framework to model adversarial strategies and enhance system resilience. The synergy between reinforcement learning and game theory establishes a robust foundation for dynamic and adaptive security in distributed systems, effectively addressing current vulnerabilities while anticipating and countering future threats. This integrated approach enables the design of resilient, scalable defense mechanisms tailored to the complex dynamics of decentralized architectures.