English
Related papers

Related papers: Towards Consistency in Adversarial Classification

200 papers

Adversarial transferability in black-box scenarios presents a unique challenge: while attackers can employ surrogate models to craft adversarial examples, they lack assurance on whether these examples will successfully compromise the target…

Machine Learning · Computer Science 2024-04-19 Mosh Levy , Guy Amit , Yuval Elovici , Yisroel Mirsky

Stochastic inverse problems are generally solved by some form of finite sampling of a space of uncertain parameters. For computationally expensive models, surrogate response surfaces are often employed to increase the number of samples used…

Numerical Analysis · Mathematics 2018-07-04 Steven Mattis , Barbara Wohlmuth

State-of-the-art machine learning models can be vulnerable to very small input perturbations that are adversarially constructed. Adversarial training is an effective approach to defend against such examples. It is formulated as a min-max…

Machine Learning · Statistics 2022-10-21 Antônio H. Ribeiro , Dave Zachariah , Thomas B. Schön

In this paper we refine the process of computing calibration functions for a number of multiclass classification surrogate losses. Calibration functions are a powerful tool for easily converting bounds for the surrogate risk (which can be…

Machine Learning · Statistics 2016-09-22 Bernardo Ávila Pires , Csaba Szepesvári

This paper studies the problem of detecting adversarial perturbations in a sequence of observations. Given a data sample $X_1, \ldots, X_n$ drawn from a standard normal distribution, an adversary, after observing the sample, can perturb…

Probability · Mathematics 2024-10-28 Gleb Smirnov

Adversarial Training is proved to be an efficient method to defend against adversarial examples, being one of the few defenses that withstand strong attacks. However, traditional defense mechanisms assume a uniform attack over the examples…

Machine Learning · Computer Science 2020-10-27 Huimin Zeng , Chen Zhu , Tom Goldstein , Furong Huang

We present a study of surrogate losses and algorithms for the general problem of learning to defer with multiple experts. We first introduce a new family of surrogate losses specifically tailored for the multiple-expert setting, where the…

Machine Learning · Computer Science 2024-04-02 Anqi Mao , Mehryar Mohri , Yutao Zhong

Adversarial examples (AEs) for DNNs have been shown to be transferable: AEs that successfully fool white-box surrogate models can also deceive other black-box models with different architectures. Although a bunch of empirical studies have…

Machine Learning · Computer Science 2025-12-17 Yechao Zhang , Shengshan Hu , Leo Yu Zhang , Junyu Shi , Minghui Li , Xiaogeng Liu , Wei Wan , Hai Jin

The choice of loss function in classification involves a fundamental trade-off: smooth losses (like Cross-Entropy) enable fast optimization rates but yield slow square-root consistency bounds, while piecewise-linear losses (like Hinge)…

Machine Learning · Computer Science 2026-05-01 Mehryar Mohri , Yutao Zhong

Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused…

Machine Learning · Statistics 2019-09-25 Roi Naveiro , Alberto Redondo , David Ríos Insua , Fabrizio Ruggeri

Despite extraordinary progress, current machine learning systems have been shown to be brittle against adversarial examples: seemingly innocuous but carefully crafted perturbations of test examples that cause machine learning predictors to…

Machine Learning · Computer Science 2023-06-14 Omar Montasser

We study losses for binary classification and class probability estimation and extend the understanding of them from margin losses to general composite losses which are the composition of a proper loss with a link function. We characterise…

Machine Learning · Statistics 2009-12-18 Mark D. Reid , Robert C. Williamson

Structured prediction involves learning to predict complex structures rather than simple scalar values. The main challenge arises from the non-Euclidean nature of the output space, which generally requires relaxing the problem formulation.…

Machine Learning · Statistics 2024-11-19 Junjie Yang , Matthieu Labeau , Florence d'Alché-Buc

Adversarial transferability refers to the capacity of adversarial examples generated on the surrogate model to deceive alternate, unexposed victim models. This property eliminates the need for direct access to the victim model during an…

Computer Vision and Pattern Recognition · Computer Science 2026-02-27 Xiaosen Wang , Zhijin Ge , Bohan Liu , Zheng Fang , Fengfan Zhou , Ruixuan Zhang , Shaokang Wang , Yuyang Luo

Consider a classification problem where we have both labeled and unlabeled data available. We show that for linear classifiers defined by convex margin-based surrogate losses that are decreasing, it is impossible to construct any…

Machine Learning · Statistics 2019-01-09 Jesse H. Krijthe , Marco Loog

It is not fully understood why adversarial examples can deceive neural networks and transfer between different networks. To elucidate this, several studies have hypothesized that adversarial perturbations, while appearing as noises, contain…

Machine Learning · Computer Science 2024-02-19 Soichiro Kumano , Hiroshi Kera , Toshihiko Yamasaki

There are a number of hypotheses underlying the existence of adversarial examples for classification problems. These include the high-dimensionality of the data, high codimension in the ambient space of the data manifolds of interest, and…

Machine Learning · Computer Science 2024-04-15 Brian Bell , Michael Geyer , David Glickenstein , Keaton Hamm , Carlos Scheidegger , Amanda Fernandez , Juston Moore

The rapid advancement of artificial intelligence within the realm of cybersecurity raises significant security concerns. The vulnerability of deep learning models in adversarial attacks is one of the major issues. In adversarial machine…

Cryptography and Security · Computer Science 2024-04-18 Khushnaseeb Roshan , Aasim Zafar

In learning problems, the noise inherent to the task at hand hinders the possibility to infer without a certain degree of uncertainty. Quantifying this uncertainty, regardless of its wide use, assumes high relevance for security-sensitive…

Deep neural networks are at the forefront of machine learning research. However, despite achieving impressive performance on complex tasks, they can be very sensitive: Small perturbations of inputs can be sufficient to induce incorrect…

Computer Vision and Pattern Recognition · Computer Science 2020-09-04 Alex Serban , Erik Poll , Joost Visser