Abstract

The rapid evolution of deep learning (DL) and machine learning (ML) techniques has facilitated the rise of highly convincing synthetic media, commonly referred to as deepfakes. These manipulative media artifacts, generated through advanced artificial intelligence algorithms, pose significant challenges in distinguishing them from authentic content. Given their potential to be disseminated widely across various online platforms, the imperative for robust detection methodologies becomes apparent. Accordingly, this study explores the efficacy of existing ML/DL-based approaches and aims to compare which type of methodology performs better in identifying deepfake content. In response to the escalating threat posed by deepfakes, previous research efforts have focused on inventing detection models leveraging CNN architectures. However, despite promising results, many of these models exhibit limitations in reproducibility and practicality when confronted with real-world scenarios. To address these challenges, this study endeavors to develop a more generalized detection framework capable of discerning deepfake content across diverse datasets. By training simple yet effective ML and DL models on a curated Wilddeepfake dataset, this research assesses the viability of detecting authentic media from deepfake counterparts. Through comparative analysis and evaluation of model performance, this study aims to contribute to the advancement of reliable deepfake detection methodologies. The models used in this study have shown significant accuracies in classifying deepfake media.

Advisor

Rushit Dave

Committee Member

Rajeev Bukralia

Committee Member

Mansi Bhavsar

Date of Degree

2024

Language

english

Document Type

Thesis

Degree

Master of Science (MS)

Program of Study

Data Science

Department

Computer Information Science

College

Science, Engineering and Technology

Download

Included in

Data Science Commons

Share

COinS
 

Rights Statement

In Copyright