Jiawei Yuan
University of Massachusetts-Dartmouth, MA·Computer Science
Drones are increasingly guided by artificial intelligence (AI), but adding AI to flying machines opens new ways for attackers to cause harm. This work studies the security of AI-assisted drones and also looks at how to train computer science students to think like security experts.
- Fields
Computer Science
Engineering
Education Research
- Topics
cybersecurity
unmanned aerial vehicles
drones
- Grants
- 2 known grants, through Sep 2027
What they work on
- Design and build an integrated, extensible research platform for securely combining AI with unmanned aerial vehicles (drones). The platform is meant to support studies that find weaknesses and test defenses.
- Analyze the security of AI-based drone anomaly detection, which flags abnormal drone behavior. Build attacks that exploit its weaknesses and measure their impact.
- Develop methods that keep AI-assisted drone operations robust in adversarial environments, where attackers try to disrupt them.
- Develop threat-driven "build it, break it, fix it" lab modules that fit into non-security computer science courses. Identify suitable courses and design multi-level integration strategies.
- Study learning paths and links across courses so that cybersecurity skills transfer from module to module. Adapt the modules for K-12 webinars, summer camps and online repositories.
More about the research
The two projects share a common thread: finding weaknesses in systems, exploiting them, and then designing fixes.
Why it matters
Drones support military, civilian and commercial work, so finding and fixing the weaknesses that AI adds could make drone operations safer from attack. Cybersecurity jobs are projected to grow far faster than jobs overall. Lab modules that build a security mindset across ordinary computer science courses could help prepare a larger, better-trained cybersecurity workforce.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Qi Lu
University of Texas Rio Grande Valley, TX·Computer Science
Develop a decentralized algorithm that plans multiple shortest routes at once, so that UAVs (aerial drones) can explore promising locations on demand, collecting data quickly while saving energy for the ground robots in the swarm.
Sheikh Rabiul Islam
University at Albany, NY·Computer Science
Develop seven AI4SecureCI learning modules that teach fair and explainable AI for securing cloud cyberinfrastructure, covering topics from malware detection to adversarial attacks, and integrate them into undergraduate and graduate courses.
Abdollah Homaifar
North Carolina A & T State University, NC·Engineering
Characterize combined trojan and adversarial attacks on deep learning-based UAV navigation, where a model resists ordinary attacks but turns malicious when a hidden trojan trigger is present.
The school
University of Massachusetts-Dartmouth: 2 labs on PI Pages, $42M a year on research, 30 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.