Bicoptor 2.0: Addressing Challenges in Probabilistic Truncation for Enhanced Privacy-Preserving Machine Learning

arXiv:2309.04909v2 Announce Type: replace
Abstract: This paper primarily focuses on analyzing the problems and proposing solutions for the probabilistic truncation protocol in existing PPML works from the perspectives of accuracy and efficiency. In terms of accuracy, we reveal that precision selections recommended in some of the existing works are incorrect. We conduct a thorough analysis of their open-source code and find that their errors were mainly due to simplified implementation, more specifically, fixed numbers are used instead of random numbers …

accuracy arxiv challenges cs.cr efficiency machine machine learning perspectives privacy problems protocol reveal solutions terms