LATIDIA · Ciberseguridad

TENNOR: Ejecución confiable para redes neuronales a través del olvido y las recuperaciones

arXiv: 2605.07160v3Tipo de anuncio: reemplazar Resumen: El entrenamiento de redes neuronales en datos confidenciales en entornos de nube no confiables requiere simultáneamente lograr eficiencia computacional y rigurosas garantías de privacidad. S

La noticia

arXiv:2605.07160v3 Announce Type: replace Abstract: Training neural networks on sensitive data in untrusted cloud environments requires simultaneously achieving computational efficiency and rigorous privacy guarantees. Sparsification techniques, essential for scalable training of wide layers, expose input-dependent memory-access patterns that are visible and can be exploited by a host OS/hypervisor, even when computation is protected by a Trusted Execution Environment. We present TENNOR, a system that resolves this tension by co-designing the neural network training pipeline with doubly oblivious primitives, eliminating value-dependent neural network access-pattern leakage while also utilizing adaptive sparsification. TENNOR recasts sparse neuron activation as a locality-sensitive hashing (LSH) retrieval problem, reducing secure sparsification to doubly oblivious accesses over an