Paper finds optimal membership inference strategies for machine learning models.
problem Determining if a sample was part of the training set of a machine learning model.
method Derives optimal strategies for membership inference with assumptions on parameter distribution, showing that black-box attacks are as good as white-box attacks.
result Optimal strategies are not tractable, leading to approximations that outperform existing methods.
This paper analyzes how differential privacy and data skewness affect membership inference attacks.
problem Membership inference attacks on privately trained models.
method Developed MPLens system to evaluate membership inference vulnerability.
result Membership inference risk is higher with skewed training data and differential privacy has trade-offs.
Directional and pairwise measurements are often used to model inter-relationships in a social network setting. The Mixed-Membership Stochastic Blockmodel (MMSB) was a seminal work in this area, and many of its capabilities were extended since then. In this paper, we propose the \emph{Dynamic Infinite Mixed-Membership s…
In this article we discuss some of the consequences of the mixed membership perspective on time series analysis. In its most abstract form, a mixed membership model aims to associate an individual entity with some set of attributes based on a collection of observed data. Although much of the literature on mixed members…
Probabilistic fair clustering tackles uncertain group membership.
problem Fair clustering with imperfect group membership.
method Probabilistic algorithms for metric graphs and metric membership.
result Approximation ratio guarantees for fair clustering.
Mixed membership factorization is a popular approach for analyzing data sets that have within-sample heterogeneity. In recent years, several algorithms have been developed for mixed membership matrix factorization, but they only guarantee estimates from a local optimum. Here, we derive a global optimization (GOP) algor…
The \emph{Mixed-Membership Stochastic Blockmodel (MMSB)} is a popular framework for modeling social network relationships. It can fully exploit each individual node's participation (or membership) in a social structure. Despite its powerful representations, this model makes an assumption that the distributions of relat…
Paper revisits set membership estimation for linear systems with relaxed disturbance bounds.
problem Set membership estimation for linear systems with disturbances bounded by convex sets.
method Adopted block-martingale small-ball condition and random perturbed control policies to establish convergence rates.
result Established convergence rates for disturbances bounded by general convex sets.
Paper evaluates membership inference attacks on transfer learning models.
problem Evaluating membership inference attacks on transfer learning models.
method Shadow model training strategy to derive data for membership inference classifier.
result Membership inference attacks can achieve effective performance against transfer learning models.
The paper tests for association between latent community memberships in multi-view network data.
problem Evaluating the independence of latent community memberships in multi-view network data.
method Extended stochastic block model for two-view network data, developed a new hypothesis test.
result Evidence of weak association between latent community memberships in binary interaction and co-complex association data.
Proposes a new privacy notion for membership inference attacks on machine learning models.
problem Membership inference attacks on machine learning models.
method Introduces f-Membership Inference Privacy (f-MIP) and μ-Gaussian Membership Inference Privacy (μ-GMIP) to quantify and mitigate privacy risks. result Analyzes likelihood ratio-based attacks and derives μ-GMIP guarantees for stochastic gradient descent (SGD) models. Study shows membership inference requires many more samples than training data.
problem Membership inference attacks require more reference samples than training data.
method Investigated the sample complexity for membership inference in Gaussian mean estimation.
result Ω(n + n^2 ρ^2) samples are necessary for successful membership inference attacks.
Overparameterized models are more vulnerable to membership inference attacks.
problem Vulnerability of overparameterized models to membership inference attacks.
method Theoretical and empirical analysis of overparameterized linear and ridge-regularized linear regression models in the Gaussian data setting.
result Increased number of parameters and model complexity increase vulnerability to membership inference attacks.
New attacks can infer model training membership using only label predictions, not confidence.
problem Inferring whether a data point was used to train a machine learning model.
method Evaluate model's predicted labels under perturbations to infer membership.
result Label-only attacks perform as well as confidence-based attacks and break defenses that rely on confidence masking.
Study membership inference under skewed priors and adaptive thresholds, improving attack accuracy.
problem Membership inference in imbalanced settings with selective thresholding.
method Developed PPV metric for skewed priors, threshold selection procedure, and a new inference attack.
result Improved inference attack accuracy in imbalanced settings.
Human labeling of data can be very time-consuming and expensive, yet, in many cases it is critical for the success of the learning process. In order to minimize human labeling efforts, we propose a novel active learning solution that does not rely on existing sources of unlabeled data. It uses a small amount of labeled…
Study modular concept learning with different oracle interfaces.
problem Learning a concept that is a cross product of component concepts.
method Analyze different types of oracle interfaces and queries.
result Modular concept learning is easier with positive examples and membership queries.
Paper presents membership encoding for deep learning models to protect training data.
problem Protecting training data from inference attacks and ensuring copyright.
method Membership encoding algorithm for deep neural networks.
result Membership information can be encoded for a subset of training data, robust to model compression and fine-tuning.
New attacks reveal membership in label-only ML models.
problem Vulnerability of ML models to membership inference attacks.
method Developed decision-based membership inference attacks.
result Label-only exposures are vulnerable to membership leakage.
Robust Trimmed k-means improves clustering with outliers and mixed data.
problem Real-world data often contains outliers and mixed membership clusters, complicating traditional clustering methods.
method Proposes Robust Trimmed k-means (RTKM) that robustifies k-means for both single- and multi-membership data.
result RTKM outperforms other methods on multi-membership data with outliers and single membership data with outliers.
Neural Bloom Filters learn set membership in one shot.
problem Efficient set membership for high-throughput data.
method Meta-learning approach to train neural networks for set membership.
result Neural Bloom Filters achieve significant compression gains.
Machine learning models leak information about the datasets on which they are trained. An adversary can build an algorithm to trace the individual members of a model's training dataset. As a fundamental inference attack, he aims to distinguish between data points that were part of the model's training set and any other…
This paper introduces Bounded Fuzzy Possibilistic Method (BFPM) by addressing several issues that previous clustering/classification methods have not considered. In fuzzy clustering, object's membership values should sum to 1. Hence, any object may obtain full membership in at most one cluster. Possibilistic clustering…
Novel network model estimates mixed-membership structure with covariate information.
problem Estimating latent mixed-membership structure in networks with covariate information.
method Proposes a novel network model that incorporates both community information and node covariate similarities.
result Achieves optimal estimation accuracy for similarity matrix and mixed-membership.
In this paper we propose a new membership attack method called co-membership attacks against deep generative models including Variational Autoencoders (VAEs) and Generative Adversarial Networks (GANs). Specifically, membership attack aims to check whether a given instance x was used in the training data or not. A co-me…
New method for mixed memberships using symmetrized Laplacian inverse matrix.
problem Mixed memberships in community detection.
method Spectral clustering on symmetrized Laplacian inverse matrix.
result Mixed-SLIM methods outperform state-of-the-art methods.
Optimal algorithm finds if point is in convex hull of distributions.
problem Determining if a point is inside the convex hull of means of multiple distributions.
method Thompson-CHM algorithm with modular design of stopping and sampling rules.
result First asymptotically optimal algorithm for CHM problem in one dimension.
The paper proposes a new model to analyze directed networks and accurately estimate community memberships.
problem Modeling and estimating community memberships in directed networks with heterogeneous degrees.
method Directed Degree Corrected Mixed Membership (DiDCMM) model and DiMSC algorithm.
result The proposed DiMSC algorithm is asymptotically consistent and provides error bounds for community membership vectors.
Model explanations can leak sensitive training data information, posing privacy risks.
problem Privacy risks of model explanations that expose training data information.
method Membership inference attacks on feature-based model explanations.
result Backpropagation-based explanations reveal statistical information about decision boundaries, leaking training data membership.
New defense DMP preserves ML model utility while enhancing membership privacy.
problem Membership inference attacks (MIAs) on machine learning models.
method Knowledge distillation to train ML models with membership privacy.
result DMP provides significantly better tradeoffs between membership privacy and classification accuracies.
Observations consisting of measurements on relationships for pairs of objects arise in many settings, such as protein interaction and gene regulatory networks, collections of author-recipient email, and social networks. Analyzing such data with probabilisic models can be delicate because the simple exchangeability assu…
DiMMSB models directed mixed membership networks, identifying distinct community structures.
problem Modeling directed mixed membership networks with distinct community structures.
method Directed Mixed Membership Stochastic Blockmodel (DiMMSB) with DiSP algorithm.
result DiSP algorithm is asymptotically consistent and outperforms competitors.
privGAN protects synthetic data from membership inference attacks.
problem Membership inference attacks on synthetic data generated by GANs.
method Developed a new GAN architecture (privGAN) that not only generates synthetic data but also defends against membership inference attacks.
result privGAN provides protection against membership inference attacks without significantly compromising downstream performance.
New attack reveals memorization patterns in pre-trained LLMs.
problem Determining if a data point was part of a pre-trained LLM's training set.
method Adapts MIA statistical tests to LLM's perplexity dynamics of subsequences.
result Significantly outperforms prior approaches in membership inference attacks.
New method calibrates white-box MI attacks, outperforming previous black-box methods.
problem Calibrating membership inference attacks on white-box models.
method Leveraging model memorization and overfitting features.
result Calibrated attack provides high precision in membership inference.
SIMPLE method quantifies uncertainty in network membership profiles.
problem Quantifying statistical uncertainty in network membership profiles.
method Degree-corrected mixed membership model, Hotelling-type statistics.
result Established exact limiting distributions of test statistics.
A new, low-cost method speeds up membership inference attacks on large language models.
problem Membership inference attacks on large language models.
method An ensemble of small quantile regression models to determine model training set membership.
result Comparable or improved accuracy with significantly reduced computational cost.
The paper develops methods to infer membership probabilities and rank network nodes using the DCMM model.
problem Understanding the latent structure of network data, especially in mixed-membership models.
method Degree-Corrected Mixed Membership (DCMM) model, novel finite-sample expansion, asymptotic distributions, confidence intervals, multiplier bootstrap method.
result Valid inference on membership probabilities and node rankings, quantifying uncertainty.
Proposes a new model for mixed membership in Gaussian mixture.
problem Limited to single component membership in Gaussian mixture models.
method Mixed membership sub-Gaussian model, spectral algorithm.
result Estimation error can be made arbitrarily small with high probability.
New method bounds membership inference attack success using mutual information.
problem Vulnerability of deep neural networks to membership inference attacks.
method Extended Fano's inequality to measure mutual information between inputs and activations.
result Empirical evaluation shows strong correlation between mutual information and model susceptibility.
Machine unlearning can compromise privacy, study shows.
problem Machine unlearning may leave data imprints in ML models, risking privacy.
method Proposed a membership inference attack to detect leakage.
result Machine unlearning can lead to unintended privacy risks.
BFPM improves machine learning accuracy by considering object types and memberships flexibly.
problem Inaccurate learning due to missing important parameters.
method BFPM relaxes fuzzy and possibilistic constraints, allowing arbitrary object memberships and movement analysis.
result BFPM enhances object movement analysis and provides flexible search space.
SIMPLE-RC method tests group membership profiles in large networks with weak signals.
problem Testing group membership profiles in large networks with weak signals.
method Random coupling technique to construct maximum SIMPLE tests for subsampled node pairs.
result Asymptotic distributions of SIMPLE-RC test are derived, enabling delicate analysis.
New insights into Valiant's learnability model reveal classes learnable with membership queries.
problem Which classes are learnable in Valiant's original model?
method Characterization using poly-size adaptive query-compression schemes and techniques for arbitrary domains.
result Learnability in Valiant's model is sandwiched between PAC and query-less variants, with halfspaces learnable with queries.
Paper explores how poisoning data can increase privacy risks in machine learning models.
problem Increasing privacy risks of benign training samples through data poisoning attacks.
method Proposes generic and optimization-based attacks to amplify membership exposure.
result Demonstrates substantial increase in membership inference precision with minimal model performance degradation.
Paper tackles MIAs vulnerability by controlling FDR, providing guarantees on false discoveries.
problem Vulnerability of deep learning models to membership inference attacks (MIAs).
method Designs a novel membership inference attack method that provides FDR guarantees.
result Demonstrates the effectiveness of the method in various settings.
Regularization can improve both privacy and performance in machine learning models.
problem Privacy vs. Utility trade-off in machine learning models.
method The study uses logistic regression with ridge regularization and a leave-one-out analysis tool.
result Increasing the number of parameters can improve both privacy and performance when coupled with proper regularization.
A method to control false membership rate in unsupervised mixture models.
problem Controlling misclassification in ambiguous datasets.
method Develops a plug-in procedure with theoretical guarantees on FMR.
result The false membership rate does not exceed the pre-defined nominal level α.