Three Tools for Practical Differential Privacy
Differentially private learning on real-world data poses challenges for standard machine learning practice: privacy guarantees are difficult to interpret, hyperparameter tuning on private data reduces the privacy budget, and ad-hoc privacy attacks are often required to test model privacy. We introduce three tools to make differentially private machine learning more practical: (1) simple sanity checks which can be carried out in a centralized manner before training, (2) an adaptive clipping bound to reduce the effective number of tuneable privacy parameters, and (3) we show that large-batch training improves model performance.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningSimilar Papers 제목 키워드 기반
Differentially Private Change-Point Detection
The change-point detection problem seeks to identify distributional changes at an unknown change-point k* in a stream of data. This problem appears in many important practical settings involving personal data, including …
Change Point DetectionFault DetectionImproving the Privacy and Practicality of Objective Perturbation for Differentially Private Linear Learners
In the arena of privacy-preserving machine learning, differentially private stochastic gradient descent (DP-SGD) has outstripped the objective perturbation mechanism in popularity and interest. Though unrivaled in versat…
Privacy PreservingregressionImproving Sparse Vector Technique with Renyi Differential Privacy
The Sparse Vector Technique (SVT) is one of the most fundamental algorithmic tools in differential privacy (DP). It also plays a central role in the state-of-the-art algorithms for adaptive data analysis and model-agnost…
Black-Box Auditing of Quantum Model: Lifted Differential Privacy with Quantum Canaries
Quantum machine learning (QML) promises significant computational advantages, yet models trained on sensitive data risk memorizing individual records, creating serious privacy vulnerabilities. While Quantum Differential …
Quantum Machine LearningLDP-FL: Practical Private Aggregation in Federated Learning with Local Differential Privacy
Train machine learning models on sensitive user data has raised increasing privacy concerns in many areas. Federated learning is a popular approach for privacy protection that collects the local gradient information inst…
Federated Learning