Deepfakes Detection in Images/Video/Audio

Primary supervisor

Abhinav Dhall

Deepfakes detection deals with machine learning methods, which detect if an image/video/audio sample is manipulated with a generative AI software. In recent years, deepfakes have been increasingly used for malicious purposes, including financial fraud, misinformation campaigns, identity theft, and cyber harassment. The ability to generate highly realistic synthetic content poses a serious threat to digital security, privacy, and trust in media. This project will develop methods for detecting deepfakes.

Student cohort

Single Semester
Double Semester

Aim/outline

Create neural networks, which can detect if image/video/audio samples are AI manipulated.

URLs/references

1. One Million Deepfakes Detection Challenge - https://arxiv.org/abs/2409.06991

2. Not made for each other- Audio-Visual Dissonance-based Deepfake Detection and Localization, ACM Multimedia 2020. https://arxiv.org/abs/2005.14405

3. AV-Deepfake1M: A large-scale LLM-driven audio-visual deepfake dataset, ACM Multimedia 2024. https://dl.acm.org/doi/abs/10.1145/3664647.3680795

4. Fake Buster Tool - https://youtu.be/XZvybwXpm_g?t=3 

Required knowledge

Python programming

Should have credited NLP or Intelligent Image & Video Analysis or Deep Learning or Machine Learning unit (exceptions can be made in case relevant experience can be demonstrated).