Metraipolis › archive › dc_ab93bf7e8523
Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning — arXiv:2609.38339
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.38339
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:43:32.145Z
- SHA-256 of the archived text
c51064c6f1eff0f863e6def75b37cbc1025b1ae33fbafaed0898d337e46c7dba- Stable URL of this page
https://metraipolis.com/documento/dc_ab93bf7e8523
How to cite
Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning — arXiv:2609.38339 — arXiv (en), https://arxiv.org/abs/2609.38339 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ab93bf7e8523 (Metraipolis archive dc_ab93bf7e8523, sha256 c51064c6f1eff0f863e6def75b37cbc1025b1ae33fbafaed0898d337e46c7dba)
BibTeX
@misc{dcab93bf7e8523,
title = {Aegis: Generative Gradient Masking for Privacy-Preserving Medical Federated Learning — arXiv:2609.38339},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.38339},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ab93bf7e8523; sha256 c51064c6f1eff0f863e6def75b37cbc1025b1ae33fbafaed0898d337e46c7dba},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.38339. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Federated learning (FL) has become a foundational paradigm for multi-institutional medical AI, allowing hospitals and research centers to jointly train diagnostic models without exchanging patient records. This privacy promise, however, is increasingly contested: a malicious or honest-but-curious server can launch model inversion attacks (MIAs) that reconstruct private patient images directly from shared model updates, and recent scalable, closed-form attacks penetrate even secure aggregation at clinically realistic batch sizes. Existing defenses face an unsatisfactory dilemma. Gradient-perturbation methods such as differential privacy and pruning trade away the diagnostic accuracy on which clinical reliability depends, while cryptographic protocols add system complexity yet still leave updates exposed to these scalable attacks. We propose Aegis, a principled client-side defense that breaks this dilemma without perturbing patient data or modifying the FL protocol. Our key insight is that the success of every known MIA is fundamentally bounded by the local batch size relative to the model's leakage capacity; once this limit is exceeded, distinct samples collide and reconstructions collapse into indistinguishable mixtures. Aegis turns this universal bottleneck into a defense: each client superimposes onto its real update a masking gradient computed on locally synthesized, task-relevant data, deliberately pushing the effective batch beyond the attack's recovery capacity. We complement the design with theoretical convergence guarantees under standard convex assumptions and evaluate Aegis on MNIST, CIFAR-10, and three MedMNIST modalities (chest X-ray, abdominal CT, colon pathology). Aegis neutralizes three state-of-the-art MIAs while preserving model utility and incurring only modest overhead, offering a practical privacy primitive for medical FL. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.38339 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-07T12:14:13.858Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).