Null-Calibrated Conformal Selection via Target-Membership Scores
problem Identifying test candidates whose unknown responses fall in a target region while controlling the false discovery rate
method Membership-score-based conformal selection
result Finite-sample valid null p-values
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.
This paper quantifies how hard it is to identify specific data points in machine learning models.
problem Quantifying the difficulty of identifying specific data points in machine learning models.
method Characterizing optimal attacks and privacy defences, deriving impacts of noise and misspecification, and proposing a new covariance attack.
result The Mahalanobis distance explains the hardness of fixed-target membership inference attacks.
Large capacity machine learning (ML) models are prone to membership inference attacks (MIAs), which aim to infer whether the target sample is a member of the target model's training dataset. The serious privacy concerns due to the membership inference have motivated multiple defenses against MIAs, e.g., differential pr…
We quantitatively investigate how machine learning models leak information about the individual data records on which they were trained. We focus on the basic membership inference attack: given a data record and black-box access to a model, determine if the record was in the model's training dataset. To perform members…
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 uses model's generalization gap to predict membership inference attacks.
problem Predicting membership inference attacks on machine learning models.
method Uses the model's generalization gap as a metric to estimate the vulnerability to membership inference attacks.
result Demonstrates that the model's generalization gap provides an upper bound on MIA security.
This paper analyzes how data and model properties affect membership inference attacks.
problem Understanding and mitigating the vulnerability of machine learning models to membership inference attacks.
method Empirical analysis of data and model properties on MIA success.
result Data and model properties, not just model overfitting, influence MIA success.
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.
Quantile regression attacks outperform shadow models in unseen class membership inference attacks.
problem Failure of shadow model attacks on unseen classes due to limited data access.
method Quantile regression attacks that learn features of member examples.
result Quantile regression attacks achieve up to 11x higher TPR than shadow model-based approaches.
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.
Paper introduces attacks to infer GAN training dataset properties.
problem Security and privacy risks of generative models like GANs.
method Proposes a general attack pipeline for two attack scenarios.
result Demonstrates strong performance in inferring GAN training dataset properties.
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.
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. A new hybrid fuzzy-crisp clustering algorithm addresses imbalanced cluster sizes.
problem Imbalanced influence in fuzzy c-means clustering for large vs. small clusters.
method Hybrid fuzzy-crisp algorithm combining linear and quadratic membership functions, setting exact zero membership for sufficiently distant points.
result The hybrid algorithm outperforms conventional fuzzy and crisp clustering methods on imbalanced datasets.
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.
New attacks improve privacy audits by analyzing model updates.
problem Improving privacy audits of AI models through sequence analysis.
method Developed SeMI attacks to identify target insertions in model sequences.
result SeMI attacks achieve higher power and tighter privacy audits.
New framework tackles stochastic latent subgroup heterogeneity in online decision-making.
problem Stochastic latent heterogeneity in online decision-making where individual responses vary with unobserved subgroups.
method Latent heterogeneous bandit framework using EM-greedy algorithm to learn subgroup probabilities and reward parameters.
result Achieves optimal estimation and classification guarantees, revealing a fundamental stochastic barrier in online decision-making.
Study compares federated learning and coreset approaches for privacy in distributed machine learning.
problem Measuring privacy in distributed machine learning approaches.
method Comparison of federated learning and coreset approaches using membership inference attack.
result Federated learning offers better privacy than coreset, but with higher communication cost.
New perspective on distribution shift helps make learning easier.
problem Learning with different training and target distributions.
method Formalizing and exploring Positive Distribution Shift (PDS).
result Distribution shift can be positive, making learning easier.
Poisoning datasets can reveal private details of other users' training points.
problem Integrity and privacy of machine learning training data.
method Active inference attacks that poison a small fraction of the training dataset.
result Poisoning as little as 0.1% of the training dataset can significantly boost inference attacks.
We use partial class memberships in soft classification to model uncertain labelling and mixtures of classes. Partial class memberships are not restricted to predictions, but may also occur in reference labels (ground truth, gold standard diagnosis) for training and validation data. Classifier performance is usually ex…
Marich extracts high-fidelity models from public data with minimal queries.
problem Creating an accurate replica of a target ML model using few queries.
method Sequentially selects informative queries to maximize entropy and reduce model mismatch.
result Extracted models achieve 60-95% of target model's accuracy with 1,000-8,500 queries.
New bounds on machine learning data leakage identified.
problem Machine Learning models can leak sensitive information.
method Formalized attack setups, derived universal bounds, studied mutual information.
result Connected attack success rate to generalization gap and mutual information.
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.
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.
Membership inference attacks seek to infer the membership of individual training instances of a privately trained model. This paper presents a membership privacy analysis and evaluation system, called MPLens, with three unique contributions. First, through MPLens, we demonstrate how membership inference attack methods …
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.
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.
New method assesses individual training points' privacy risk without retraining.
problem Privacy vulnerability of individual training points in membership inference attacks.
method Derives a closed-form decomposition of individual black-box MIA vulnerability, extending to deep networks.
result Proposes a surrogate score operating on last-layer representations that requires only a single trained model.
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.
The arms race between attacks and defenses for machine learning models has come to a forefront in recent years, in both the security community and the privacy community. However, one big limitation of previous research is that the security domain and the privacy domain have typically been considered separately. It is t…
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…
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. Machine learning algorithms, when applied to sensitive data, pose a distinct threat to privacy. A growing body of prior work demonstrates that models produced by these algorithms may leak specific private information in the training data to an attacker, either through the models' structure or their observable behavior.…
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.
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.
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 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.
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.
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…
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…
A new model estimates mixed memberships for categorical data with weighted responses.
problem Limited applicability of existing GoM model to weighted categorical data.
method Proposes Weighted Grade of Membership (WGoM) model, relaxing distribution constraints.
result WGoM can describe any response matrix with finite distinct elements.
We consider the problem of estimating community memberships of nodes in a network, where every node is associated with a vector determining its degree of membership in each community. Existing provably consistent algorithms often require strong assumptions about the population, are computationally expensive, and only p…
Membership inference determines, given a sample and trained parameters of a machine learning model, whether the sample was part of the training set. In this paper, we derive the optimal strategy for membership inference with a few assumptions on the distribution of the parameters. We show that optimal attacks only depe…
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.
We show that the Membership Problem for finitely generated subgroups of 3-manifold groups is solvable.
Log-Loss scores expose membership privacy breaches.
problem Privacy leakage from statistical aggregates like Log-Loss scores.
method Proved that Log-Loss scores enable full accuracy membership inference in a single query.
result Complete membership privacy breach is possible with Log-Loss scores.