DeepGuard is a state-of-the-art forensic AI system designed to detect AI-generated images with high accuracy. Using hybrid models combining handcrafted features and deep learning architectures, DeepGuard analyzes pixel-level inconsistencies, PRNU patterns, and transformer-based embeddings to flag manipulated visuals. It's lightweight, explainable, and optimized for both speed and reliability, making it suitable for forensic investigators, researchers, and commercial deployment. As deepfakes grow more realistic, tools like DeepGuard are no longer optional, they're essential.
Researcher in AI and cybersecurity, School of Computing, Mathematics and Physics, University of Portsmouth. UK Global Talent Visa, endorsed by UKRI. About · Google Scholar · LinkedIn