Hanieh Totonchi Asl, Ebrahim Nouri, Zhuoran Li, Danella Zhao · 2026 · arXiv
DOI: 10.48550/arXiv.2610.27431 · open-access PDF
El aprendizaje automático preservador de la privacidad (PPML) ofrece un camino prometedor para llevar a los servicios de IA potentes a la vanguardia sin exponer datos de usuario sensibles. Sin embargo, su implementación práctica sigue restringida por los altos costos de comunicación, computación y movimiento de datos de la computación multipartidaria segura (MPC), especialmente durante la inferencia no lineal. Los sistemas MPC existentes suelen desconectar la generación de aleatoriedad relacionada independientemente de la entrada de la ejecución en línea, creando una presión de memoria sustancial para buffer los datos criptográficos de un solo uso.
Machine translation (Meta M2M100); the English original follows.
Privacy-preserving machine learning (PPML) offers a promising path toward bringing powerful AI services to the edge without exposing sensitive user data. However, its practical deployment remains constrained by the high communication, computation, and data-movement costs of secure multi-party computation (MPC), particularly during nonlinear inference. Existing MPC systems typically decouple input-independent correlated randomness generation from online execution, creating substantial memory pressure to buffer single-use cryptographic data. Moreover, limited storage can force a stop-and-refill
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.27431, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange