摘要
机器人与机器学习每日新闻的一位新闻记者兼新闻编辑-机器学习的最新研究结果已经发表。根据澳大利亚Ultimo的新闻报道,By NewsRx编辑,研究表明:“模型反转攻击涉及到重建目标模型的训练数据,这引起了机器学习模型的严重隐私问题。然而,这些攻击,特别是基于学习的MET HOD,很可能受到攻击精度低的影响,即机器学习分类器对这些重建数据的分类精度低。”
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – Current study results on Machine Learn ing have been published. According to news reporting out of Ultimo, Australia, b y NewsRx editors, research stated, “Model inversion attacks involve reconstructi ng the training data of a target model, which raises serious privacy concerns fo r machine learning models. However, these attacks, especially learning-based met hods, are likely to suffer from low attack accuracy, i.e., low classification ac curacy of these reconstructed data by machine learning classifiers.”