arXiv research

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

We define and study the problem of modular concept learning, that is, learning a concept that is a cross product of component concepts. If an element's membership in a concept depends solely on it's membership in the components, learning the concept as a whole can be reduced to learning the components. We analyze this …

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…

New algorithms save computation in agnostic learning with membership queries.

New algorithm learns decision trees faster than before.

Log-Loss scores expose membership privacy breaches.

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 algorithm learns halfspaces almost optimally with fewer queries.

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…

Adaptive querying learns user psychometrics with AI personas.

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

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

New perspective on distribution shift helps make learning easier.

Efficiently estimate Boolean product distribution parameters from truncated samples.

LoRA and privacy: Random projections help but not always.

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

Paper tackles efficient HMM learning with conditional samples.

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

Paper evaluates membership inference attacks on transfer learning models.

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 …

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 …

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

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

Proposes a new privacy notion for membership inference attacks on machine learning models.

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…

Proposes a new model for mixed membership in Gaussian mixture.

Overparameterized models are more vulnerable to membership inference attacks.

Enhances MMSB for complex graph structures with HL-MRF priors.

Study quantized models' privacy against membership inference attacks.

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…

BFPM improves machine learning accuracy by considering object types and memberships flexibly.

Machine learning as a service (MLaaS), and algorithm marketplaces are on a rise. Data holders can easily train complex models on their data using third party provided learning codes. Training accurate ML models requires massive labeled data and advanced learning algorithms. The resulting models are considered as intell…

We construct and analyze active learning algorithms for the problem of binary classification with abstention. We consider three abstention settings: \emph{fixed-cost} and two variants of \emph{bounded-rate} abstention, and for each of them propose an active learning algorithm. All the proposed algorithms can work in th…

Community detection is the task of detecting hidden communities from observed interactions. Guaranteed community detection has so far been mostly limited to models with non-overlapping communities such as the stochastic block model. In this paper, we remove this restriction, and provide guaranteed community detection f…

New method uses model's generalization gap to predict membership inference attacks.

Study shows membership inference requires many more samples than training data.

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…

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…

New attacks reveal membership in label-only ML models.

New method for mixed memberships using symmetrized Laplacian inverse matrix.

Algorithm learns latent simplex from perturbed points in input-sparsity time.

Data privacy is an important issue for "machine learning as a service" providers. We focus on the problem of membership inference attacks: given a data sample and black-box access to a model's API, determine whether the sample existed in the model's training data. Our contribution is an investigation of this problem in…

Robust Trimmed k-means improves clustering with outliers and mixed data.

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

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