Matthew Wright
Rochester Institute of Technology, NY·Computer Science
Generative AI makes fake images and videos easy to produce, and malicious software increasingly targets the billions of connected devices around us. Both trends threaten trust in digital systems.
- Fields
Computer Science
Engineering
- Topics
cybersecurity
digital forensics
deepfakes
- Grants
- 2 known grants, through Sep 2027
What they work on
- Study how users evaluate suspect digital content through qualitative interviews and user studies, and use the findings to integrate multiple AI-content forensic tools into one navigable platform.
- Develop explanation methods, game-based training scenarios and ethical frameworks that help users understand and responsibly apply the outputs of digital content forensic tools.
- Build a malware detection model that works across different IoT operating systems and chip architectures by mapping similar code functions into a common embedding space.
- Make IoT malware detectors efficient on low-power devices by applying model compression techniques adapted from explainable AI and model pruning.
- Use large language models to restyle malware code so it evades existing classifiers, and apply the results to design a moving-target defense.
More about the research
These two collaborative projects address each threat. One builds tools that help people judge whether digital content is genuine. The other builds machine-learning detectors for malware on Internet-of-Things devices.
Why it matters
Journalists, investigators and other professionals who must judge whether online content is authentic could gain a single, easier-to-use set of forensic tools and training. This may help limit the spread of AI-generated deception. Hospitals, transportation and industry rely on IoT devices that are increasingly attacked, and lightweight, robust malware detectors and shared datasets could help protect those systems.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Jie Yan
Bowie State University, MD·Computer Science
Investigate the sources of hallucination — fabricated or inaccurate output — when large language models are applied to digital forensic casework, and develop techniques that reduce it enough for results to align with evidentiary standards.
Siwei Lyu
University at Buffalo, NY·Computer Science
Strengthen deepfake detectors against anti-forensic attacks by processing each input with a randomly chosen model from an infinite ensemble of classifiers, making detectors harder to fool.
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.
The school
Rochester Institute of Technology: 9 labs on PI Pages, $78M a year on research, 65 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.