Skip to main content

Pretom Roy Ovi

Title: Assistant Professor

Department: Data Science

College: College of Information

Curriculum Vitae

Curriculum Vitae Link

Education

  • PhD, University of Maryland, Baltimore, MD, 2024
    Major: Information Systems
    Dissertation: "A Robust Federated Learning against Cyber Instrusions to Ensure Data Confidentiality and Model Integrity"
  • MS, University of Maryland, Baltimore County, 2021
    Major: Information Systems

Current Scheduled Teaching

DTSC 5505.401Applied Machine Learning for Data ScientistsSpring 2025
Texas Education Code 51.974 (HB 2504) requires each institution of higher education to make available to the public, a syllabus for undergraduate lecture courses offered for credit by the institution.

Previous Scheduled Teaching

DTSC 5505.020Applied Machine Learning for Data ScientistsFall 2024 SPOT
Texas Education Code 51.974 (HB 2504) requires each institution of higher education to make available to the public, a syllabus for undergraduate lecture courses offered for credit by the institution.

Published Intellectual Contributions

    Conference Proceeding

  • Ovi, P. (2023). A Comprehensive Study of Gradient Inversion Attacks in Federated Learning and Baseline Defense Strategies.
  • Ovi, P. (2023). Confident Federated Learning to Tackle Label Flipped Data Poisoning Attacks.
  • Ovi, P. (2023). Mixed Quantization Enabled Federated Learning to Tackle Gradient Inversion Attacks.
  • Ovi, P. (2022). Secured Federated Training: Detecting Compromised Nodes and Identifying the Type of Attacks.
  • Ovi, P. (2022). TinyM2Net: A Flexible System Algorithm Co-designed Multimodal Learning Framework for Tiny Devices.
  • Ovi, P. (2022). Towards Developing Data Security Aware Federated Learning for Multimodal Contested Environment.
  • Ovi, P. (2021). ARIS: A Real-Time Edge Computed Accident Risk Inference System.
,
Overall
Summative Rating		 Challenge and
Engagement Index		 Response Rate

out of 5
out of 7		 %
of
students responded
  • Overall Summative Rating (median):
    This rating represents the combined responses of students to the four global summative items and is presented to provide an overall index of the class’s quality. Overall summative statements include the following (response options include a Likert scale ranging from 5 = Excellent, 3 = Good, and 1= Very poor):
    • The course as a whole was
    • The course content was
    • The instructor’s contribution to the course was
    • The instructor’s effectiveness in teaching the subject matter was
  • Challenge and Engagement Index:
    This rating combines student responses to several SPOT items relating to how academically challenging students found the course to be and how engaged they were. Challenge and Engagement Index items include the following (response options include a Likert scale ranging from 7 = Much higher, 4 = Average, and 1 = Much lower):
    • Do you expect your grade in this course to be
    • The intellectual challenge presented was
    • The amount of effort you put into this course was
    • The amount of effort to succeed in this course was
    • Your involvement in course (doing assignments, attending classes, etc.) was
CLOSE