The K-Space Signature: Frequency-Domain Representation Learning for Medical Deepfake Detection
Ranking
Observed public metrics from 1 member.
Merged summary
TL;DR - An arXiv preprint proposing K-Space Signature (KSS), a frequency-domain forensic framework for detecting AI-generated "medical deepfakes" in 3D MRI. It matters because synthetic medical imaging, while useful for privacy-preserving data sharing, can be weaponized, and this offers a near-perfect detector that generalizes to unseen scanners.
- KSS moves analysis into the spectral domain and subtracts an empirical global anatomical prior in Logarithmic Power Spectral Density (Log-PSD) space, suppressing macroscopic anatomical variance to expose hardware and generative traces.
- Detection uses a 3D MLP-Mixer with an ArcFace metric-learning head, chosen deliberately over CNNs because spectral artifacts are globally distributed and CNNs carry a local spatial bias.
- On multi-center 3D MRI with multiple generators, the method reports >0.99 Accuracy and ROC-AUC; zero-shot transfer to independent datasets from entirely unseen scanners holds up to 0.93 Accuracy.
- Source code and pre-trained models are promised publicly upon acceptance; no external baseline comparisons or ablation details are given in the abstract.
Sources (1)
The K-Space Signature: Frequency-Domain Representation Learning for Medical Deepfake Detection
TL;DR - An arXiv preprint proposing K-Space Signature (KSS), a frequency-domain forensic framework for detecting AI-generated "medical deepfakes" in 3D MRI. It matters because synthetic medical imaging, while useful for privacy-preserving data sharing, can be weaponized, and this offers a near-perfect detector that generalizes to unseen scanners.
- KSS moves analysis into the spectral domain and subtracts an empirical global anatomical prior in Logarithmic Power Spectral Density (Log-PSD) space, suppressing macroscopic anatomical variance to expose hardware and generative traces.
- Detection uses a 3D MLP-Mixer with an ArcFace metric-learning head, chosen deliberately over CNNs because spectral artifacts are globally distributed and CNNs carry a local spatial bias.
- On multi-center 3D MRI with multiple generators, the method reports >0.99 Accuracy and ROC-AUC; zero-shot transfer to independent datasets from entirely unseen scanners holds up to 0.93 Accuracy.
- Source code and pre-trained models are promised publicly upon acceptance; no external baseline comparisons or ablation details are given in the abstract.