Matthew Wright Headshot

Matthew Wright

Director Research Global Cybersecurity Inst

Global Cybersecurity Institute
Golisano College of Computing and Information Sciences
Director of Research for the Global Cybersecurity Institute

585-475-5432
Office Location
GCI-3783
Office Mailing Address
152 Lomb Memorial Drive Rochester, NY 14623

Matthew Wright

Director Research Global Cybersecurity Inst

Global Cybersecurity Institute
Golisano College of Computing and Information Sciences
Director of Research for the Global Cybersecurity Institute

Education

BS, Harvey Mudd College; MS, Ph.D., University of Massachusetts at Amherst

Bio

Matt Wright is the Director of Research for the Global Cybersecurity Institute and a Professor of Computing Security. He graduated with his PhD from the Department of Computer Science at the University of Massachusetts in May, 2005, where he earned his MS in 2002. His dissertation work examined attacks and defenses of systems that provide anonymity online. His other interests include adversarial machine learning and understanding the human element of security. Previously, he earned his BS degree in Computer Science at Harvey Mudd College. He has been the lead investigator on over $3.7 million in funded projects, including an NSF CAREER award, and he has published 100 peer-reviewed papers, including numerous contributions in the most prestigious venues focused on computer security and privacy. Learn more: https://sites.google.com/site/matthewkwright/

585-475-5432

Areas of Expertise

Select Scholarship

Journal Paper
Al-Ameen, Mahdi Nasrullah and Matthew Wright. "A Comprehensive Study of the GeoPass User Authentication Scheme." Interacting with Computers. (2016): 1-1. Web.
Al-Ameen, Mahdi Nasrullah and Matthew Wright. "iPersea: Towards Improving the Sybil-resilience of Social DHT." Journal of Network and Computer Applications 71. (2016): 1-10. Web.
Al-Ameen, Mahdi Nasrullah, S M Taiabul Haque, and Matthew Wright. "Leveraging Autobiographical Memory for Two-factor Online Authentication." Information and Computer Security 24. 4 (2016): 386-399. Print.
Barton, Armon and Matthew Wright. "DeNASA: Destination-Naive AS-Awareness in Anonymous Communications." Proceedings on Privacy Enhancing Technologies 2016. 4 (2016): 356—372. Web.
Published Conference Proceedings
Juarez, Marc, et al. "WTF-PAD: Toward an Efficient Website Fingerprinting Defense." Proceedings of the European Symposium on Research in Computer Security (ESORICS). Ed. Ioannis Askoxylakis, et al. Heraklion, Greece: Springer, 2016. Print.

Currently Teaching

CSEC-720
3 Credits
This course covers the intersection of cybersecurity and deep learning technologies such as CNNs, LSTMs, and GANs. Topics include the application of deep learning to traffic analysis, Deepfake detection, malware classification, fooling deep learning classifiers with adversarial examples, network attack prediction and modeling, poisoning attacks, and privacy attacks like model inversion and membership inference. Students will present research papers, perform several exercises to apply attack and defense techniques, and complete a final research project. Prior experience with machine learning concepts and implementation is required, but necessary details on deep learning will be covered.
CSEC-520
3 Credits
The course provides students an opportunity to explore methods and applications in cyber analytics with advanced machine learning algorithms including deep learning. Students will learn how to use machine learning methods to solve cybersecurity problems such as network security, anomaly detection, malware analysis, etc. Students will also learn basic concepts and algorithms in machine learning such as clustering, neural networks, adversarial machine learning, etc. Students taking this course should have the 4th year status and completed MATH-190 Discrete Math, MATH-251 Probability and Statistics I, and MATH-241 Linear Algebra.
CSEC-620
3 Credits
The course provides students an opportunity to explore methods and applications in cyber analytics with advanced machine learning algorithms including deep learning. Students will learn how to use machine learning methods to solve cybersecurity problems such as network security, anomaly detection, malware analysis, etc. Students will also learn basic concepts and algorithms in machine learning such as clustering, neural networks, adversarial machine learning, etc. A key component of the course will be an independent exploratory project to solve a security program with machine learning algorithms. Students taking this course should have knowledge in Discrete Math, Probability and Statistics, and Linear Algebra. Students should also be able to program in Python.

In the News