Skip to content
AK
Back to all projects

Computer Vision

Academic project

Explainable Deepfake and Image Forgery Detection

Problem

Manipulated images and deepfakes are difficult to judge from a prediction alone, so a detector must also show why it flagged an image.

System

An explainable computer-vision system that detects manipulated images using deep learning and vision transformers, then produces attention-based explanation maps to localise the suspected manipulation. The work spans the DEEPFORGE final-year project and the related ViT-Xplain research on explainable detection.

My contribution

Built the image preprocessing pipeline, trained and evaluated the vision models, implemented attention visualisation for forgery localisation, and ran the error analysis used to compare model variants.

System architecture

  1. Image input
  2. Preprocessing
  3. Vision model
  4. Manipulation prediction
  5. Attention or explanation map
  6. Forensic output

Technical focus

  • Deepfake detection
  • Forgery localisation
  • Vision transformers
  • Attention visualisation
  • Explainable AI

Technology stack

  • PyTorch
  • OpenCV
  • NumPy
  • Python

Data source

Dataset and data-collection write-up is being prepared.

Data pipeline

Ingestion and preprocessing write-up is being prepared.

Model or LLM workflow

Model and workflow write-up is being prepared.

Evaluation and results

Evaluation setup and results write-up is being prepared.

Challenges and engineering decisions

Key engineering decisions write-up is being prepared.