arXiv research

Study modular concept learning with different oracle interfaces.

New algorithm learns halfspaces with membership queries, achieving near optimal label complexity.

New insights into Valiant's learnability model reveal classes learnable with membership queries.

In this paper we study the adaptive learnability of decision trees of depth at most $d$ from membership queries. This has many applications in automated scientific discovery such as drugs development and software update problem. Feldman solves the problem in a randomized polynomial time algorithm that asks $\tilde O(2^…

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…

Log-Loss scores expose membership privacy breaches.

New algorithms save computation in agnostic learning with membership queries.

New algorithm learns decision trees faster than before.

Marich extracts high-fidelity models from public data with minimal queries.

New algorithm learns halfspaces almost optimally with fewer queries.

We introduce new combinatorial quantities for concept classes, and prove lower and upper bounds for learning complexity in several models of query learning in terms of various combinatorial quantities. Our approach is flexible and powerful enough to enough to give new and very short proofs of the efficient learnability…

New attacks can infer model training membership using only label predictions, not confidence.

Adaptive querying learns user psychometrics with AI personas.

Membership Inference Attack (MIA) determines the presence of a record in a machine learning model's training data by querying the model. Prior work has shown that the attack is feasible when the model is overfitted to its training data or when the adversary controls the training algorithm. However, when the model is no…

LoRA and privacy: Random projections help but not always.

Efficiently estimate Boolean product distribution parameters from truncated samples.

New sampler improves uniform sampling over convex bodies with fewer queries.

New perspective on distribution shift helps make learning easier.

Quantile regression attacks outperform shadow models in unseen class membership inference attacks.

Paper tackles efficient HMM learning with conditional samples.

This paper analyzes how differential privacy and data skewness affect membership inference attacks.

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…

With the widespread use of machine learning (ML) techniques, ML as a service has become increasingly popular. In this setting, an ML model resides on a server and users can query it with their data via an API. However, if the user's input is sensitive, sending it to the server is undesirable and sometimes even legally …

New method for mixed memberships using symmetrized Laplacian inverse matrix.

The paper proposes a new model to analyze directed networks and accurately estimate community memberships.

Paper evaluates membership inference attacks on transfer learning models.

DiMMSB models directed mixed membership networks, identifying distinct community structures.

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.

The paper develops methods to infer membership probabilities and rank network nodes using the DCMM model.

Probabilistic fair clustering tackles uncertain group membership.

Proposes a new model for mixed membership in Gaussian mixture.

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…

New method bounds membership inference attack success using mutual information.

Face recognition models can be inferred from student models, posing privacy risks.

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…

A new model estimates mixed memberships for categorical data with weighted responses.

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…

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.

We show that the Membership Problem for finitely generated subgroups of 3-manifold groups is solvable.

New model quantifies how much machine learning models can reveal about individual data usage.

New model for detecting communities in weighted bipartite networks.

New methods estimate mixed memberships in multi-layer networks.

Mixed-SCORE+ improves community detection in weak signal networks.

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…

A new model for detecting overlapping communities in weighted networks.