Exposing DeepFakes via Hyperspectral Domain Mapping
This addresses the challenge of detecting realistic fake images for security and media integrity, though it is incremental as it builds on spectral-domain mapping.
The paper tackled the problem of detecting DeepFakes by proposing HSI-Detect, a method that reconstructs hyperspectral images from RGB inputs to amplify manipulation artifacts, resulting in consistent improvements over RGB-only baselines on the FaceForensics++ dataset.
Modern generative and diffusion models produce highly realistic images that can mislead human perception and even sophisticated automated detection systems. Most detection methods operate in RGB space and thus analyze only three spectral channels. We propose HSI-Detect, a two-stage pipeline that reconstructs a 31-channel hyperspectral image from a standard RGB input and performs detection in the hyperspectral domain. Expanding the input representation into denser spectral bands amplifies manipulation artifacts that are often weak or invisible in the RGB domain, particularly in specific frequency bands. We evaluate HSI-Detect across FaceForensics++ dataset and show the consistent improvements over RGB-only baselines, illustrating the promise of spectral-domain mapping for Deepfake detection.