Related papers: Efficient Model Extraction via Boundary Sampling
In the domain of black-box model extraction, conventional methods reliant on soft labels or surrogate datasets struggle with scaling to high-dimensional input spaces and managing the complexity of an extensive array of interrelated classes.…
We investigate how an adversary can optimally use its query budget for targeted evasion attacks against deep neural networks in a black-box setting. We formalize the problem setting and systematically evaluate what benefits the adversary…
We present a new method for black-box adversarial attack. Unlike previous methods that combined transfer-based and scored-based methods by using the gradient or initialization of a surrogate white-box model, this new method tries to learn a…
Artificial neural networks (ANNs) have gained significant popularity in the last decade for solving narrow AI problems in domains such as healthcare, transportation, and defense. As ANNs become more ubiquitous, it is imperative to…
The transferability of adversarial examples across deep neural networks (DNNs) is the crux of many black-box attacks. Many prior efforts have been devoted to improving the transferability via increasing the diversity in inputs of some…
In the face of difficult exploration problems in reinforcement learning, we study whether giving an agent an object-centric mapping (describing a set of items and their attributes) allow for more efficient learning. We found this problem is…
Adversarial example generation becomes a viable method for evaluating the robustness of a machine learning model. In this paper, we consider hard-label black-box attacks (a.k.a. decision-based attacks), which is a challenging setting that…
Adversarial examples of deep neural networks are receiving ever increasing attention because they help in understanding and reducing the sensitivity to their input. This is natural given the increasing applications of deep neural networks…
Diffusion models have shown remarkable performance in generation problems over various domains including images, videos, text, and audio. A practical bottleneck of diffusion models is their sampling speed, due to the repeated evaluation of…
Machine learning models are critically susceptible to evasion attacks from adversarial examples. Generally, adversarial examples, modified inputs deceptively similar to the original input, are constructed under whitebox settings by…
We present a method for adversarial input generation against black box models for reading comprehension based question answering. Our approach is composed of two steps. First, we approximate a victim black box model via model extraction…
We study the problem of generating adversarial examples in a black-box setting in which only loss-oracle access to a model is available. We introduce a framework that conceptually unifies much of the existing work on black-box attacks, and…
In Explainable AI, rule extraction translates model knowledge into logical rules, such as IF-THEN statements, crucial for understanding patterns learned by black-box models. This could significantly aid in fields like disease diagnosis,…
Model extraction is a severe threat to Machine Learning-as-a-Service systems, especially through data-free approaches, where dishonest users can replicate the functionality of a black-box target model without access to realistic data.…
Adversarial attacks often involve random perturbations of the inputs drawn from uniform or Gaussian distributions, e.g., to initialize optimization-based white-box attacks or generate update directions in black-box attacks. These simple…
In model extraction attacks, adversaries can steal a machine learning model exposed via a public API by repeatedly querying it and adjusting their own model based on obtained predictions. To prevent model stealing, existing defenses focus…
While deep learning models have shown significant performance across various domains, their deployment needs extensive resources and advanced computing infrastructure. As a solution, Machine Learning as a Service (MLaaS) has emerged,…
A distribution inference attack aims to infer statistical properties of data used to train machine learning models. These attacks are sometimes surprisingly potent, but the factors that impact distribution inference risk are not well…
Model Stealing (MS) attacks allow an adversary with black-box access to a Machine Learning model to replicate its functionality, compromising the confidentiality of the model. Such attacks train a clone model by using the predictions of the…
We focus on the problem of adversarial attacks against models on discrete sequential data in the black-box setting where the attacker aims to craft adversarial examples with limited query access to the victim model. Existing black-box…