Learning-Based Difficulty Calibration for Enhanced Membership Inference Attacks

arXiv:2401.04929v2 Announce Type: replace-cross
Abstract: Machine learning models, in particular deep neural networks, are currently an integral part of various applications, from healthcare to finance. However, using sensitive data to train these models raises concerns about privacy and security. One method that has emerged to verify if the trained models are privacy-preserving is Membership Inference Attacks (MIA), which allows adversaries to determine whether a specific data point was part of a model's training dataset. While a series of MIAs have …

abstract applications arxiv attacks calibration concerns cs.ai cs.cr cs.lg data finance healthcare however inference integral machine machine learning machine learning models networks neural networks part privacy privacy and security raises security train type verify