60 papers with code • 0 benchmarks • 2 datasets
These leaderboards are used to track progress in Inference Attack
We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained.
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models
In addition, we propose the first effective defense mechanisms against such broader class of membership inference attacks that maintain a high level of utility of the ML model.
Finally, we discuss the privacy concerns associated with sharing synthetic data produced by GANs and test their ability to withstand a simple membership inference attack.
Specifically, given a black-box access to the target classifier, the attacker trains a binary classifier, which takes a data sample's confidence score vector predicted by the target classifier as an input and predicts the data sample to be a member or non-member of the target classifier's training dataset.
We transform $(\epsilon,\delta)$ to a bound on the Bayesian posterior belief of the adversary assumed by differential privacy concerning the presence of any record in the training dataset.
In this work, we introduce GradInversion, using which input images from a larger batch (8 - 48 images) can also be recovered for large networks such as ResNets (50 layers), on complex datasets such as ImageNet (1000 classes, 224x224 px).
Distribution inference attacks can pose serious risks when models are trained on private data, but are difficult to distinguish from the intrinsic purpose of statistical machine learning -- namely, to produce models that capture statistical properties about a distribution.