Related papers: Efficient Model Extraction via Boundary Sampling

Recent studies have shown that Deep Leaning models are susceptible to adversarial examples, which are data, in general images, intentionally modified to fool a machine learning classifier. In this paper, we present a multi-objective nested…

In statistics, it is common to encounter multi-modal and non-smooth likelihood (or objective function) maximization problems, where the parameters have known upper and lower bounds. This paper proposes a novel derivative-free global…

Recent masked diffusion models (MDMs) have shown competitive performance compared to autoregressive models (ARMs) for language modeling. While most literature has focused on performance enhancing sampling procedures, efficient sampling from…

This paper presents a novel method for statistical inference in high-dimensional binary models with unspecified structure, where we leverage a (potentially misspecified) sparsity-constrained working generalized linear model (GLM) to…

As machine learning methods see greater adoption and implementation in high stakes applications such as medical image diagnosis, the need for model interpretability and explanation has become more critical. Classical approaches that assess…

Subsampling methods aim to select a subsample as a surrogate for the observed sample. Such methods have been used pervasively in large-scale data analytics, active learning, and privacy-preserving analysis in recent decades. Instead of…

Given a deep neural network image classification model that we treat as a black box, and an unlabeled evaluation dataset, we develop an efficient strategy by which the classifier can be evaluated. Randomly sampling and labeling instances…

Various methods for robot design optimization have been developed so far. These methods are diverse, ranging from numerical optimization to black-box optimization. While numerical optimization is fast, it is not suitable for cases involving…

Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information."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…

Despite rigorous safety alignment, Large Language Models (LLMs) remain vulnerable to jailbreak attacks. Existing black-box methods often rely on heuristic templates or exhaustive trials, lacking mechanistic interpretability and query…

We present a novel adaptive optimization algorithm for black-box multi-objective optimization problems with binary constraints on the foundation of Bayes optimization. Our method is based on probabilistic regression and classification…

Adversarial examples are important for understanding the behavior of neural models, and can improve their robustness through adversarial training. Recent work in natural language processing generated adversarial examples by assuming…

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…

We study the task of replicating the functionality of black-box neural models, for which we only know the output class probabilities provided for a set of input images. We assume back-propagation through the black-box model is not possible…

Many software engineering tasks, such as testing, and anomaly detection can benefit from the ability to infer a behavioral model of the software.Most existing inference approaches assume access to code to collect execution sequences. In…

Model stealing attack is increasingly threatening the confidentiality of machine learning models deployed in the cloud. Recent studies reveal that adversaries can exploit data synthesis techniques to steal machine learning models even in…

Modern generative AI models, such as diffusion and flow matching models, can sample from rich data distributions. However, many applications, especially in science and engineering, require more than drawing samples from the model…

Model selection is an integral problem of model based optimization techniques such as Bayesian optimization (BO). Current approaches often treat model selection as an estimation problem, to be periodically updated with observations coming…

Recent works have shown that deep neural networks are vulnerable to adversarial examples that find samples close to the original image but can make the model misclassify. Even with access only to the model's output, an attacker can employ…

Membership inference attacks are designed to determine, using black box access to trained models, whether a particular example was used in training or not. Membership inference can be formalized as a hypothesis testing problem. The most…