【论文记录】Input Perturbation: A New Paradigm between Central and Local Differential Privacy

【论文记录】Input Perturbation: A New Paradigm between Central and Local Differential Privacy

算法&基本思想

• By line 7 in Algorithm 1, it can be seen that the noise added to the original data affects the gradient. (adds noise to original data instances, leading perturbation on the gradient and eventually causing perturbation on the model parameters)

理论分析