Date of Graduation

5-2026

Document Type

Thesis

Degree Name

Bachelor of Science in Data Science

Degree Level

Undergraduate

Department

Data Science

Advisor/Mentor

Dr. Karl Schubert

Committee Member

Dr. Elizabeth Keiffer

Second Committee Member

Dr. David Barrett

Abstract

The rapid advancements in the world of generative artificial intelligence has enabled the creation of highly realistic fictitious facial images, raising concerns about authenticity and bias in computer vision systems. This study investigates the capabilities of machine learning models to distinguish between real and artificially generated facial images across gender and race focusing on celebrity imagery. Four datasets were used against the classification model, each trained on images of a single celebrity within distinct demographic groups: White women, White men, Black women, and Black men. For each group, real images are paired with AI-generated counterparts designed to closely replicate the target individual’s facial features.

This study aims to identify whether an input image is authentic or digitally generated using binary classification. Performance is evaluated using standard classification metrics, including accuracy, precision, recall, and F1-score, allowing for side-by-side comparison across demographic categories using Google Gemini’s Nano Banana 2 for all artificially developed images. By focusing on identity and demographic variables, this study aims to assess whether detection performance varies across groups and to identify potential disparities in model effectiveness.

The results aim to provide insight into the technical capability of machine learning systems to detect AI-generated faces and the broader implications for bias in facial recognition technologies. Findings from this research contribute to the ongoing discussion surrounding the reliability and equity of AI-driven image analysis systems in the presence of increasingly sophisticated generative models.

Keywords

Artificial Intelligence, AI, photos, Convolutional Nueral Network, Comparative Model

Download

Included in

Data Science Commons

Share

COinS