When the Link Goes Dark: Morgan Students Build a Smarter Defense for Drones

Award-Winning Cybersecurity Innovation Equips Unmanned Aircraft to Detect Attacks, Respond Safely and Keep Operating When Ground Communications Fail

At altitude, a compromised drone cannot pull over, reboot or wait for help. If an attacker corrupts its sensors, spoofs its navigation signals or severs its connection to the ground, the aircraft must determine — in real time — what it can trust and how to stay safe. A Morgan State University student research team is building intelligence for precisely that moment, transforming knowledge developed in classrooms and laboratories into an award-winning cybersecurity solution with the potential to strengthen the future of autonomous flight.

Student researchers Awotwi Baffoe and David Nyarko, members of Morgan’s Data Engineering and Predictive Analytics (DEPA) Research Lab, have earned a $25,000 award through the Institute of Electrical and Electronics Engineers’ (IEEE’s) Aerospace and Electronic Systems Society (AESS) Cybersecurity Challenge Phase 2. Their proposal, “Lightweight Onboard AI for Cyber-Resilient UAV Anomaly Detection and Safe Mission Response,” was selected in the area of cybersecure and resilient avionics operation.

The international recognition, from the world’s largest technical professional organization dedicated to advancing technology for the benefit of humanity, places the Morgan team among innovators confronting one of aerospace cybersecurity’s most urgent challenges: how to protect increasingly autonomous unmanned aerial vehicles, or UAVs, from sophisticated digital attacks without relying on a constant connection to an operator, ground station or cloud platform.

That dependency is a critical weakness. Conventional security approaches often send data elsewhere for monitoring and analysis, assuming a reliable communications link will remain available. But an adversary capable of attacking an aircraft’s sensors or controls may also jam or spoof that link. The Morgan team’s answer is to move the defense onto the aircraft itself.

Their proposed system uses a compact artificial intelligence model that runs directly on a UAV’s onboard computer. Designed to operate within the tight size, weight and power limits of flight hardware, the model continuously learns the patterns of normal behavior across the aircraft’s sensors and control systems. When activity departs from those patterns, the system assesses whether the change reflects ordinary turbulence or equipment wear, or evidence of tampering and compromise.

The innovation goes beyond detecting a threat. Once the system identifies a likely attack, it is designed to help the aircraft respond safely without waiting for instructions that may never arrive. Depending on the situation, the UAV could isolate an affected subsystem, switch to a trusted sensor source, enter a reduced-capability mode or initiate a safe recovery or landing maneuver. Instead of failing outright, the aircraft can degrade gracefully, preserving safety and mission integrity as conditions change.

“Unmanned aircraft are being asked to fly further from their operators and make more decisions on their own, and that makes onboard security a safety problem, not just an IT problem,” said Baffoe, team co-lead. “Our approach is to give the aircraft the ability to recognize when something is wrong and respond safely without waiting on a link back to the ground.”

The project reflects the kind of applied, interdisciplinary learning taking place at Morgan, where students are connecting data engineering, machine learning, cybersecurity and electrical and computer engineering to address a complex real-world need. The work will be conducted in the DEPA Research Lab, within Morgan’s Center for Equitable Artificial Intelligence and Machine Learning Systems, or CEAMLS.

Faculty advisers guiding the project include Kelechi Nwachukwu, adjunct faculty member and engineering manager for data engineering and predictive analytics in Morgan’s Department of Electrical and Computer Engineering; Peter Taiwo, D.Eng., a CEAMLS faculty researcher and lecturer with the DEPA Research Lab; and Kofi Nyarko, D.Eng., professor of Electrical and Computer Engineering and director of CEAMLS and the DEPA Research Lab.

Morgan submitted the proposal May 15, 2026, and received notice of its selection June 19 from Southwest Research Institute, which administers the challenge. The IEEE Aerospace and Electronic Systems Society initiative focuses on developing secure, resilient avionics to protect future flight, UAVs and broader aerospace systems from software and hardware exploits. It emphasizes the use of artificial intelligence and machine learning to mitigate cyber-physical threats and provides participants with specialized datasets, simulation tools and an open-source federated learning framework for developing and evaluating scalable solutions.

As part of the award process, the review committee asked the Morgan team to broaden the project’s scope to address two challenge problems, collaborate with an industry partner and publish the resulting software in a public repository. The team accepted those conditions and will complete the work during a three-month performance period. Grant contracting is being coordinated through the Georgia Tech Research Institute.

Making the software publicly available will extend the project’s value well beyond a single competition. Researchers across aerospace, cybersecurity and autonomous systems will be able to examine the work, test it and build on the team’s findings, turning a Morgan-developed solution into a shared foundation for further innovation.

“Being selected by IEEE AESS is a strong endorsement of the work our students and faculty are doing at Morgan,” said Baffoe. “And the fact that we will be releasing this software publicly means the results will serve the broader research community as well.”

For Nyarko, the honor continues a record of student innovation with practical reach. This past spring, he was part of Team AgroVision, which earned national recognition and a $50,000 award for a modular hydroponic farming system. The award supported marketing and accelerated deployment of that project. His contributions to both teams illustrate the breadth of research opportunities available to Morgan students, and their capacity to apply technical expertise to challenges spanning food systems, artificial intelligence, cybersecurity and areas beyond.

The latest recognition also advances Morgan’s growing research profile in AI-enabled cybersecurity for aerospace and unmanned systems. More importantly, it demonstrates what becomes possible when students are empowered to move from theory to experimentation and from experimentation to impact: they can create technology that answers the demands of the day, contribute openly to a global research community and represent Morgan on an international stage.

The next milestone for Baffoe, Nyarko and their faculty advisers is not simply completing an award-winning idea. It is proving that a small, efficient layer of onboard intelligence can help an aircraft recognize danger, protect itself and find a safe path forward — even when the connection to the ground goes silent.

Legal Disclaimer:

EIN Presswire provides this news content "as is" without warranty of any kind. We do not accept any responsibility or liability for the accuracy, content, images, videos, licenses, completeness, legality, or reliability of the information contained in this article. If you have any complaints or copyright issues related to this article, kindly contact the author above.