DPAdapter: Improving Differentially Private Deep Learning through Noise Tolerance Pre-training

arXiv:2403.02571v1 Announce Type: new
Abstract: Recent developments have underscored the critical role of \textit{differential privacy} (DP) in safeguarding individual data for training machine learning models. However, integrating DP oftentimes incurs significant model performance degradation due to the perturbation introduced into the training process, presenting a formidable challenge in the {differentially private machine learning} (DPML) field. To this end, several mitigative efforts have been proposed, typically revolving around formulating new DPML algorithms or relaxing DP definitions to harmonize with distinct contexts. …

abstract arxiv challenge cs.cv cs.lg data deep learning differential differential privacy machine machine learning machine learning models noise performance presenting pre-training privacy process role through training type