English
Related papers

Related papers: Adversarial Attacks on Gaussian Process Bandits

200 papers

We consider a contextual bandit problem with a combinatorial action set and time-varying base arm availability. At the beginning of each round, the agent observes the set of available base arms and their contexts and then selects an action…

Machine Learning · Computer Science 2025-09-26 Andi Nika , Sepehr Elahi , Cem Tekin

In recent years, research on adversarial attacks has become a hot spot. Although current literature on the transfer-based adversarial attack has achieved promising results for improving the transferability to unseen black-box models, it…

Computer Vision and Pattern Recognition · Computer Science 2021-08-11 Zheng Yuan , Jie Zhang , Yunpei Jia , Chuanqi Tan , Tao Xue , Shiguang Shan

Stochastic linear contextual bandit algorithms have substantial applications in practice, such as recommender systems, online advertising, clinical trials, etc. Recent works show that optimal bandit algorithms are vulnerable to adversarial…

Machine Learning · Statistics 2023-01-31 Qin Ding , Cho-Jui Hsieh , James Sharpnack

Even though deep learning has shown unmatched performance on various tasks, neural networks have been shown to be vulnerable to small adversarial perturbations of the input that lead to significant performance degradation. In this work we…

Machine Learning · Computer Science 2020-03-23 Evgenii Zheltonozhskii , Chaim Baskin , Yaniv Nemcovsky , Brian Chmiel , Avi Mendelson , Alex M. Bronstein

Adversarial perturbations dramatically decrease the accuracy of state-of-the-art image classifiers. In this paper, we propose and analyze a simple and computationally efficient defense strategy: inject random Gaussian noise, discretize each…

Machine Learning · Computer Science 2019-03-27 Yuchen Zhang , Percy Liang

Implicit Neural Representations (INRs) have been recently garnering increasing interest in various research fields, mainly due to their ability to represent large, complex data in a compact, continuous manner. Past work further showed that…

Machine Learning · Computer Science 2026-03-04 Tamir Shor , Ethan Fetaya , Chaim Baskin , Alex Bronstein

Adversarial perturbations aim to deceive neural networks into predicting inaccurate results. For visual object trackers, adversarial attacks have been developed to generate perturbations by manipulating the outputs. However, transformer…

Computer Vision and Pattern Recognition · Computer Science 2024-11-27 Fatemeh Nourilenjan Nokabadi , Jean-Francois Lalonde , Christian Gagné

Bayesian optimization is an effective technique for black-box optimization, but its applicability is typically limited to low-dimensional and small-budget problems due to the cubic complexity of computing the Gaussian process (GP)…

Machine Learning · Computer Science 2025-12-18 Yunyue Wei , Vincent Zhuang , Saraswati Soedarmadji , Yanan Sui

Bayesian optimization is a powerful global optimization technique for expensive black-box functions. One of its shortcomings is that it requires auxiliary optimization of an acquisition function at each iteration. This auxiliary…

Machine Learning · Statistics 2014-02-28 Ziyu Wang , Babak Shakibi , Lin Jin , Nando de Freitas

Variational Gaussian process (GP) approximations have become a standard tool in fast GP inference. This technique requires a user to select variational features to increase efficiency. So far the common choices in the literature are…

Machine Learning · Statistics 2021-10-26 Veit Wild , George Wynne

We focus on the problem of black-box adversarial attacks, where the aim is to generate adversarial examples for deep learning models solely based on information limited to output label~(hard label) to a queried data input. We propose a…

Machine Learning · Computer Science 2021-06-14 Satya Narayan Shukla , Anit Kumar Sahu , Devin Willmott , J. Zico Kolter

Sparse variational Gaussian processes (GPs) construct tractable posterior approximations to GP models. At the core of these methods is the assumption that the true posterior distribution over training function values ${\bf f}$ and inducing…

Machine Learning · Computer Science 2025-06-27 Michalis K. Titsias

Latency attacks against object detection represent a variant of adversarial attacks that aim to inflate the inference time by generating additional ghost objects in a target image. However, generating ghost objects in the black-box scenario…

Computer Vision and Pattern Recognition · Computer Science 2024-04-25 Erh-Chung Chen , Pin-Yu Chen , I-Hsin Chung , Che-Rung Lee

Adversarial attacks, particularly the Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) pose significant threats to the robustness of deep learning models in image classification. This paper explores and refines defense…

Cryptography and Security · Computer Science 2025-05-15 Hetvi Waghela , Jaydip Sen , Sneha Rakshit

Adversarial attacks have emerged as a major challenge to the trustworthy deployment of machine learning models, particularly in computer vision applications. These attacks have a varied level of potency and can be implemented in both white…

Computer Vision and Pattern Recognition · Computer Science 2025-03-04 Nandish Chattopadhyay , Abdul Basit , Bassem Ouni , Muhammad Shafique

Gaussian processes (GP) provide a prior over functions and allow finding complex regularities in data. Gaussian processes are successfully used for classification/regression problems and dimensionality reduction. In this work we consider…

Machine Learning · Computer Science 2016-11-21 Pavel Izmailov , Dmitry Kropotov

Bayesian Optimization using Gaussian Processes is a popular approach to deal with the optimization of expensive black-box functions. However, because of the a priori on the stationarity of the covariance matrix of classic Gaussian…

Machine Learning · Statistics 2019-05-10 Ali Hebbal , Loic Brevault , Mathieu Balesdent , El-Ghazali Talbi , Nouredine Melab

Adversarial example (AE) is an attack method for machine learning, which is crafted by adding imperceptible perturbation to the data inducing misclassification. In the current paper, we investigated the upper bound of the probability of…

Machine Learning · Computer Science 2025-03-20 Hiroaki Maeshima , Akira Otsuka

Building surrogate models is one common approach when we attempt to learn unknown black-box functions. Bayesian optimization provides a framework which allows us to build surrogate models based on sequential samples drawn from the function…

Machine Learning · Computer Science 2021-09-17 Hengrui Luo , James W. Demmel , Younghyun Cho , Xiaoye S. Li , Yang Liu

This paper discusses a scenario approach to robust optimization of a blackbox function in a bandit setting. We assume that the blackbox function can be modeled as a Gaussian Process (GP) for every realization of the uncertain parameter. We…

Optimization and Control · Mathematics 2018-05-01 Shaunak D. Bopardikar , Vaibhav Srivastava