Expertise

  • Machine Learning, Artificial Intelligence, Cybersecurity, Computer Vision, Data Science

Research Interests

  • Adversarial Machine Learning, Federated Learning, Anomaly Detection, Medical Imaging, Safety of Artificial Intelligence
Back to Faculty

Kenneth Co, PhD

Assistant Professor


Academic Background

  • PhD in Computing, Imperial College London
  • Master of Science in Computing (Machine Learning), Imperial College London
  • Master of Arts in Mathematics, Johns Hopkins University
  • Bachelor of Arts in Mathematics, Johns Hopkins University

Professional and Academic Experience

  • Machine Learning Consultant, Thinking Machines
  • Research Scientist, DataSpartan UK

Affiliations, Awards, and Honors

  • 2023 Endorsement for Global Talent Visa, Royal Academy of Engineering, United Kingdom
  • 2020 3rd Place, CSAW’20 Cybersecurity Applied Research Competition, Europe, hosted by New York University (NYU) and Grenoble INP-ESISAR
  • 2018-2022 PhD Programme Funding, Department of Computing, Imperial College London
  • 2016 J.J. Sylvester Undergraduate Award, Department of Mathematics, Johns Hopkins University
  • 2016 Applied Mathematics and Statistics Achievement Award, Department of Applied Mathematics and Statistics, Johns Hopkins University
  • 2015 Naddor Prize, Department of Applied Mathematics and Statistics, Johns Hopkins University
  • 2012-2016 Woodrow Wilson Research Fellow, Johns Hopkins University
  • 2012 Bronze Medalist, International Mathematical Olympiad (IMO), Mar del Plata, Argentina

PEER-REVIEWED CONFERENCE PROCEEDINGS

  • Castiglione, L. M., Hau, Z., Co, K. T., Muñoz-González, L., Teng, F., & Lupu, E. (2022). HA-Grid: Security Aware Hazard Analysis for Smart Grids. In Proceedings of the 2022 IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm), 446-452. https://doi.org/10.1109/SmartGridComm52983.2022.9961003
  • Co, K. T., Muñoz-González, L., Kanthan, L., Glocker, B., & Lupu, E. C. (2021). Universal adversarial robustness of texture and shape-biased models. In Proceedings of the 2021 IEEE International Conference on Image Processing (ICIP), 799-803. https://doi.org/10.1109/ICIP42928.2021.9506325
  • Co, K. T., Muñoz-González, L., de Maupeou, S., & Lupu, E. C. (2019). Procedural noise adversarial examples for black-box attacks on deep convolutional networks. In Proceedings of the 2019 ACM SIGSAC Conference on Computer and Communications Security (CCS '19), 275–289. https://doi.org/10.1145/3319535.3345660

BOOK CHAPTER

  • Muñoz-González, L., Carnerero-Cano, J., Co, K. T., & Lupu, E. C. (2019). Challenges and Advances in Adversarial Machine Learning. Resilience and Hybrid Threats, 102-120.

This website uses information-gathering tools, such as cookies, web analytics, and other similar technology. By using this website, you consent to the use of these tools.

View Privacy Policy