Privacy Leakage Avoidance with Switching Ensembles
We consider membership inference attacks, one of the main privacy issues in machine learning. These recently developed attacks have been proven successful in determining, with confidence better than a random guess, whether a given sample belongs to the dataset on which the attacked machine learning model was trained. Several approaches have been developed to mitigate this privacy leakage but the tradeoff performance implications of these defensive mechanisms (i.e., accuracy and utility of the defended machine learning model) are not well studied yet. We propose a novel approach of privacy leakage avoidance with switching ensembles (PASE), which both protects against current membership inference attacks and does that with very small accuracy penalty, while requiring acceptable increase in training and inference time. We test our PASE method, along with the the current state-of-the-art PATE approach, on three calibration image datasets and analyze their tradeoffs.
Code (0)
등록된 구현이 없습니다.
Tasks
BIG-bench Machine LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
In Differential Privacy, There is Truth: On Vote Leakage in Ensemble Private Learning
When learning from sensitive data, care must be taken to ensure that training algorithms address privacy concerns. The canonical Private Aggregation of Teacher Ensembles, or PATE, computes output labels by aggregating th…
Privacy-Preserving Distributed Learning for Residential Short-Term Load Forecasting
In the realm of power systems, the increasing involvement of residential users in load forecasting applications has heightened concerns about data privacy. Specifically, the load data can inadvertently reveal the daily r…
Federated LearningLoad ForecastingPrivacy PreservingEnsembling Membership Inference Attacks Against Tabular Generative Models
Membership Inference Attacks (MIAs) have emerged as a principled framework for auditing the privacy of synthetic data generated by tabular generative models, where many diverse methods have been proposed that each exploi…
PAPILLON: Privacy Preservation from Internet-based and Local Language Model Ensembles
Users can divulge sensitive information to proprietary LLM providers, raising significant privacy concerns. While open-source models, hosted locally on the user's machine, alleviate some concerns, models that users can h…
Language ModelingLanguage ModellingOn the Importance of Neural Membrane Potential Leakage for LIDAR-based Robot Obstacle Avoidance using Spiking Neural Networks
Using neuromorphic computing for robotics applications has gained much attention in recent year due to the remarkable ability of Spiking Neural Networks (SNNs) for high-precision yet low memory and compute complexity inf…
Robot Navigation