{"ID":2844702,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.06104","arxiv_id":"2511.06104","title":"PraxiMLP: A Threshold-based Framework for Efficient Three-Party MLP with Practical Security","abstract":"Efficiency and communication cost remain critical bottlenecks for practical Privacy-Preserving Machine Learning (PPML). Most existing frameworks rely on fixed-point arithmetic for strong security, which introduces significant precision loss and requires expensive cross-domain conversions (e.g., Arithmetic-to-Boolean) for non-linear operations. To address this, we propose PraxiMLP, a highly efficient three-party MLP framework grounded in practical security. The core of our work is a pair of novel additive-to-multiplicative conversion protocols that operate entirely within the arithmetic domain, thus avoiding expensive cross-domain conversions. By natively supporting loating-point numbers, PraxiMLP precisely handles non-linear functions, dramatically improving both efficiency and precision. Experimental results confirm that, compared to mainstream PPML frameworks, PraxiMLP delivers an average 8 orders of magnitude precision improvement on basic protocols and a 5x average model training speedup in a WAN environment.","short_abstract":"Efficiency and communication cost remain critical bottlenecks for practical Privacy-Preserving Machine Learning (PPML). Most existing frameworks rely on fixed-point arithmetic for strong security, which introduces significant precision loss and requires expensive cross-domain conversions (e.g., Arithmetic-to-Boolean) f...","url_abs":"https://arxiv.org/abs/2511.06104","url_pdf":"https://arxiv.org/pdf/2511.06104v1","authors":"[\"Tianle Tao\",\"Shizhao Peng\",\"Haogang Zhu\"]","published":"2025-11-08T18:56:26Z","proceeding":"cs.CR","tasks":"[\"cs.CR\"]","methods":"[]","has_code":false}