English
Related papers

Related papers: Persistent Classification: A New Approach to Stabi…

200 papers

Deep neural networks (DNNs) are shown to be vulnerable to adversarial examples. A well-trained model can be easily attacked by adding small perturbations to the original data. One of the hypotheses of the existence of the adversarial…

Machine Learning · Computer Science 2022-10-04 Jiancong Xiao , Liusha Yang , Yanbo Fan , Jue Wang , Zhi-Quan Luo

Adversarial training, as one of the most effective defense methods against adversarial attacks, tends to learn an inclusive decision boundary to increase the robustness of deep learning models. However, due to the large and unnecessary…

Computer Vision and Pattern Recognition · Computer Science 2022-07-19 Xiaoyu Liang , Yaguan Qian , Jianchang Huang , Xiang Ling , Bin Wang , Chunming Wu , Wassim Swaileh

Adversarial attacks on deep-learning models pose a serious threat to their reliability and security. Existing defense mechanisms are narrow addressing a specific type of attack or being vulnerable to sophisticated attacks. We propose a new…

Machine Learning · Computer Science 2023-06-22 Mouna Rabhi , Roberto Di Pietro

Machine learning systems based on deep neural networks, being able to produce state-of-the-art results on various perception tasks, have gained mainstream adoption in many applications. However, they are shown to be vulnerable to…

Machine Learning · Computer Science 2018-01-16 Bo Luo , Yannan Liu , Lingxiao Wei , Qiang Xu

We explore rigorous, systematic, and controlled experimental evaluation of adversarial examples in the real world and propose a testing regimen for evaluation of real world adversarial objects. We show that for small scene/ environmental…

Computer Vision and Pattern Recognition · Computer Science 2020-03-17 Brett Jefferson , Carlos Ortiz Marrero

Given the apparent difficulty of learning models that are robust to adversarial perturbations, we propose tackling the simpler problem of developing adversarially robust features. Specifically, given a dataset and metric of interest, the…

Machine Learning · Computer Science 2024-08-27 Shivam Garg , Vatsal Sharan , Brian Hu Zhang , Gregory Valiant

Adversarial training tends to result in models that are less accurate on natural (unperturbed) examples compared to standard models. This can be attributed to either an algorithmic shortcoming or a fundamental property of the training data…

Machine Learning · Computer Science 2021-07-02 Alireza Mousavi Hosseini , Amir Mohammad Abouei , Mohammad Hossein Rohban

The existence of adversarial examples has been a mystery for years and attracted much interest. A well-known theory by \citet{ilyas2019adversarial} explains adversarial vulnerability from a data perspective by showing that one can extract…

Machine Learning · Computer Science 2024-05-07 Ang Li , Yifei Wang , Yiwen Guo , Yisen Wang

We study the robustness of machine learning approaches to adversarial perturbations, with a focus on supervised learning scenarios. We find that typical phase classifiers based on deep neural networks are extremely vulnerable to adversarial…

Disordered Systems and Neural Networks · Physics 2024-01-26 Si Jiang , Sirui Lu , Dong-Ling Deng

We develop an asymptotic theory of adversarial estimators ('A-estimators'). They generalize maximum-likelihood-type estimators ('M-estimators') as their average objective is maximized by some parameters and minimized by others. This class…

Econometrics · Economics 2022-06-20 Jonas Metzger

Adversarial attacks - input perturbations imperceptible to humans that fool neural networks - remain both a persistent failure mode in machine learning, and a phenomenon with mysterious origins. To shed light, we define and analyze a…

Machine Learning · Computer Science 2026-03-12 Alessandro Salvatore , Stanislav Fort , Surya Ganguli

Recent works have shown that the input domain of any machine learning classifier is bound to contain adversarial examples. Thus we can no longer hope to immune classifiers against adversarial examples and instead can only aim to achieve the…

Machine Learning · Computer Science 2020-09-25 Gil Fidel , Ron Bitton , Ziv Katzir , Asaf Shabtai

Current research on defending against adversarial examples focuses primarily on achieving robustness against a single attack type such as $\ell_2$ or $\ell_{\infty}$-bounded attacks. However, the space of possible perturbations is much…

Machine Learning · Computer Science 2024-10-10 Sihui Dai , Chong Xiang , Tong Wu , Prateek Mittal

This work provides a computable, direct, and mathematically rigorous approximation to the differential geometry of class manifolds for high-dimensional data, along with nonlinear projections from input space onto these class manifolds. The…

Machine Learning · Computer Science 2023-08-24 Aaron Mahler , Tyrus Berry , Tom Stephens , Harbir Antil , Michael Merritt , Jeanie Schreiber , Ioannis Kevrekidis

Recent studies have found that deep learning systems are vulnerable to adversarial examples; e.g., visually unrecognizable adversarial images can easily be crafted to result in misclassification. The robustness of neural networks has been…

Computer Vision and Pattern Recognition · Computer Science 2018-09-25 Chia-Yi Hsu , Pei-Hsuan Lu , Pin-Yu Chen , Chia-Mu Yu

This paper proposes an attack-independent (non-adversarial training) technique for improving adversarial robustness of neural network models, with minimal loss of standard accuracy. We suggest creating a neighborhood around each training…

Machine Learning · Computer Science 2021-07-28 Bronya Roni Chernyak , Bhiksha Raj , Tamir Hazan , Joseph Keshet

The existence of adversarial examples underscores the importance of understanding the robustness of machine learning models. Bayesian neural networks (BNNs), due to their calibrated uncertainty, have been shown to posses favorable…

Machine Learning · Computer Science 2020-12-24 Matthew Yuan , Matthew Wicker , Luca Laurenti

Recently, anomaly scores have been formulated using reconstruction loss of the adversarially learned generators and/or classification loss of discriminators. Unavailability of anomaly examples in the training data makes optimization of such…

Computer Vision and Pattern Recognition · Computer Science 2024-10-28 Muhammad Zaigham Zaheer , Jin Ha Lee , Arif Mahmood , Marcella Astrid , Seung-Ik Lee

Despite their numerous successes, there are many scenarios where adversarial risk metrics do not provide an appropriate measure of robustness. For example, test-time perturbations may occur in a probabilistic manner rather than being…

Machine Learning · Statistics 2021-08-03 Benjie Wang , Stefan Webb , Tom Rainforth

We initiate the study of a new notion of adversarial loss which we call distributional adversarial loss. In this notion, we assume for each original example, the allowed adversarial perturbation set is a family of distributions, and the…

Machine Learning · Computer Science 2025-06-23 Saba Ahmadi , Siddharth Bhandari , Avrim Blum , Chen Dan , Prabhav Jain