arXiv research

Study exact community recovery in noisy SBM with limited queries.

Estimates TV distance between autoregressive models under different access models.

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods -…

LEAQI learns to query an expert less often for noisy guidance.

Query access significantly speeds up learning Multi-Index Models under Gaussian distribution.

Quantum algorithms for multi-armed bandits are explored with limited reward access.

Study reduces memory needs for active learning with enriched queries.

Paper tackles efficient HMM learning with conditional samples.

Current neural network-based classifiers are susceptible to adversarial examples even in the black-box setting, where the attacker only has query access to the model. In practice, the threat model for real-world systems is often more restrictive than the typical black-box model where the adversary can observe the full …

This work sets lower bounds on the number of score queries needed for diffusion sampling.

Fairly allocate items with noisy queries, reducing envy.

Efficient local planning with linear approximations for agents with limited simulator access.

Improves model classification accuracy in black-box settings.

Lower bounds on queries needed for finding stationary points in non-convex optimization.

Study exact partition recovery with same-cluster oracle, bounded error.

NP-Attack reduces query counts for black-box adversarial attacks.

Interactive IL algorithm queries noisy expert for feedback, reducing sample size.

Active learning method reduces label queries for positive examples.

AdaWISH improves efficiency of discrete integration queries.

In this paper, we provide a method to learn the directed structure of a Bayesian network using data. The data is accessed by making conditional probability queries to a black-box model. We introduce a notion of simplicity of representation of conditional probability tables for the nodes in the Bayesian network, that we…

FinBloom enhances LLMs for real-time financial queries.

Algorithm identifies nearest mode in noisy data.

We give algorithms for estimating the expectation of a given real-valued function $φ:X\to {\bf R}$ on a sample drawn randomly from some unknown distribution $D$ over domain $X$, namely ${\bf E}_{{\bf x}\sim D}[φ({\bf x})]$. Our algorithms work in two well-studied models of restricted access to data samples. The first o…

Machine learning (ML) models may be deemed confidential due to their sensitive training data, commercial value, or use in security applications. Increasingly often, confidential ML models are being deployed with publicly accessible query interfaces. ML-as-a-service ("predictive analytics") systems are an example: Some …

Machine learning models trained on confidential datasets are increasingly being deployed for profit. Machine Learning as a Service (MLaaS) has made such models easily accessible to end-users. Prior work has developed model extraction attacks, in which an adversary extracts an approximation of MLaaS models by making bla…

Quadratic memory is essential for optimal convex optimization queries.

We study the problem of interactively learning a binary classifier using noisy labeling and pairwise comparison oracles, where the comparison oracle answers which one in the given two instances is more likely to be positive. Learning from such oracles has multiple applications where obtaining direct labels is harder bu…

We study the most practical problem setup for evaluating adversarial robustness of a machine learning system with limited access: the hard-label black-box attack setting for generating adversarial examples, where limited model queries are allowed and only the decision is provided to a queried data input. Several algori…

Improves text-to-SQL models by selecting the best SQL query from beam output.

Study shows limitations and possibilities of learning quantum circuit output distributions.

TensorPlan algorithm finds δ-optimal policies with poly$(H,d)$ queries under linearly realizable state-value function.

Solving for adversarial examples with projected gradient descent has been demonstrated to be highly effective in fooling the neural network based classifiers. However, in the black-box setting, the attacker is limited only to the query access to the network and solving for a successful adversarial example becomes much …

We propose a framework for Semi-Supervised Active Clustering framework (SSAC), where the learner is allowed to interact with a domain expert, asking whether two given instances belong to the same cluster or not. We study the query and computational complexity of clustering in this framework. We consider a setting where…

New algorithms learn from comparisons to classify data robustly to noise.

The paper explores how to learn from incomplete online social networks.

We consider the problem of global optimization of an unknown non-convex smooth function with zeroth-order feedback. In this setup, an algorithm is allowed to adaptively query the underlying function at different locations and receives noisy evaluations of function values at the queried points (i.e. the algorithm has ac…

New methods improve black-box adversarial attacks with fewer queries.

Study active learning of PTFs with derivative access.

New algorithms learn MNL weights efficiently for any slate size.

Deep neural network (DNN) as a popular machine learning model is found to be vulnerable to adversarial attack. This attack constructs adversarial examples by adding small perturbations to the raw input, while appearing unmodified to human eyes but will be misclassified by a well-trained classifier. In this paper, we fo…

We consider the black-box adversarial setting, where the adversary has to generate adversarial perturbations without access to the target models to compute gradients. Previous methods tried to approximate the gradient either by using a transfer gradient of a surrogate white-box model, or based on the query feedback. Ho…

The paper develops algorithms to restore monotonicity in non-monotone functions.

Adaptive Misinformation defends against model stealing attacks by sending incorrect predictions for OOD queries.

Study private query release with public data, reducing sample sizes.

Proposes a query-efficient blackbox attack method.

Efficient methods for answering complex probabilistic queries in sequential data.

Optimal SQ bounds for learning binary product distributions and Ising models.

LITE models improve query-document relevance with learnable late interactions.