Newest papers

Secure Multimodal Federated Optimization via Hierarchical DNA-Based Key Management

Yuping Yan, Yaochu Jin · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27644 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

A otimização federada sobre dados multimodais estabelecidos em componentes permite que as instituições distribuídas otimizem colaborativamente um modelo compartilhado usando imagens médicas, perfis genômicos, registros clínicos e sinais fisiológicos sem centralizar dados brutos. No entanto, a proteção de dados específicos de modalidade ao longo do ciclo de vida da otimização permanece insuficientemente explorada, especialmente quando as modalidades heterogêneas exigem chaves de criptografia separadas e acesso local seletivo. Este artigo propõe uma estrutura de otimização federada multimodais segura que separa a proteção agregada de dados locais da proteção de atualização federada. Uma autoridade de gestão de chaves confiável fornece com segurança uma chave de cliente através da criptografia de chave pública híbrida (HPKE), a partir da qual cada

Machine translation (Meta M2M100); the English original follows.

Abstract

Federated optimization over heterogeneous multimodal data enables distributed institutions to collaboratively optimize a shared model using medical images, genomic profiles, clinical records, and physiological signals without centralizing raw data. However, protecting modality-specific data throughout the optimization lifecycle remains insufficiently explored, particularly when heterogeneous modalities require separate encryption keys and selective local access. This paper proposes a secure multimodal federated optimization framework that separates local data protection from federated-update protection. A trusted key-management authority securely provisions one client key through Hybrid Public Key Encryption (HPKE), from which each client locally derives modality-specific symmetric keys using the domain-separated HMAC-based Extract-and-Expand Key Derivation Function (HKDF). Heterogeneous modalities are mapped into a unified DNA-domain representation and processed through a DNA-origami-inspired structural transformation before authenticated encryption with AES-GCM. During local optimization, only the required modalities are decrypted within an authorized client environment. Individual model updates are independently protected through secure aggregation, allowing the coordinator to observe only aggregated updates rather than each client's contribution. Together, these components establish a structured approach to modality-specific protection and secure collaborative optimization, integrating hierarchical key management, authenticated local encryption, and aggregation-level update protection within a unified framework.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Computer science, Encryption, Key (lock), Key management, Modalities, Computer security

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange