A client-side test-time defense combining MAE detection with diffusion purification raises federated MRI tumor-classifier adversarial accuracy from 49.5% to 87.3% under bounded PGD attacks.
A Comprehen- sive Systematic Review of MRI Techniques for the Early Detection of Brain Tumors: Clinical Implications and Diagnostic Accuracy
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
MedFedPure: A Medical Federated Framework with MAE-based Detection and Diffusion Purification for Inference-Time Attacks
A client-side test-time defense combining MAE detection with diffusion purification raises federated MRI tumor-classifier adversarial accuracy from 49.5% to 87.3% under bounded PGD attacks.