English
Related papers

Related papers: Local Intrinsic Dimensionality Signals Adversarial…

200 papers

Local intrinsic dimension (LID) estimation methods have received a lot of attention in recent years thanks to the progress in deep neural networks and generative modeling. In opposition to old non-parametric methods, new methods use…

Machine Learning · Statistics 2024-12-24 Piotr Tempczyk , Łukasz Garncarek , Dominik Filipiak , Adam Kurpisz

Adversarial prompts are capable of jailbreaking frontier large language models (LLMs) and inducing undesirable behaviours, posing a significant obstacle to their safe deployment. Current mitigation strategies primarily rely on activating…

Computation and Language · Computer Science 2025-10-08 Canaan Yung , Hanxun Huang , Christopher Leckie , Sarah Erfani

Deep Neural Networks (DNNs) have recently achieved great success in many tasks, which encourages DNNs to be widely used as a machine learning service in model sharing scenarios. However, attackers can easily generate adversarial examples…

Machine Learning · Computer Science 2019-07-17 Xiaowei Zhou , Ivor W. Tsang , Jie Yin

The Intrinsic Dimension (ID) is a key concept in unsupervised learning and feature selection, as it is a lower bound to the number of variables which are necessary to describe a system. However, in almost any real-world dataset the ID…

Machine Learning · Statistics 2026-04-02 Antonio Di Noia , Iuri Macocco , Aldo Glielmo , Alessandro Laio , Antonietta Mira

We study the identification of a linear time-invariant dynamical system affected by large-and-sparse disturbances modeling adversarial attacks or faults. Under the assumption that the states are measurable, we develop necessary and…

Systems and Control · Electrical Eng. & Systems 2022-10-07 Han Feng , Baturalp Yalcin , Javad Lavaei

High-dimensional data commonly lies on low-dimensional submanifolds, and estimating the local intrinsic dimension (LID) of a datum -- i.e. the dimension of the submanifold it belongs to -- is a longstanding problem. LID can be understood as…

Machine Learning · Computer Science 2024-10-28 Hamidreza Kamkari , Brendan Leigh Ross , Rasa Hosseinzadeh , Jesse C. Cresswell , Gabriel Loaiza-Ganem

Despite much effort, deep neural networks remain highly susceptible to tiny input perturbations and even for MNIST, one of the most common toy datasets in computer vision, no neural network model exists for which adversarial perturbations…

Computer Vision and Pattern Recognition · Computer Science 2018-09-21 Lukas Schott , Jonas Rauber , Matthias Bethge , Wieland Brendel

The manifold hypothesis asserts that data of interest in high-dimensional ambient spaces, such as image data, lies on unknown low-dimensional submanifolds. Diffusion models (DMs) -- which operate by convolving data with progressively larger…

Machine Learning · Computer Science 2025-10-14 Kin Kwan Leung , Rasa Hosseinzadeh , Gabriel Loaiza-Ganem

What fundamentally distinguishes an adversarial attack from a misclassification due to limited model expressivity or finite data? In this work, we investigate this question in the setting of high-dimensional binary classification, where…

Machine Learning · Statistics 2025-06-17 Matteo Vilucchio , Lenka Zdeborová , Bruno Loureiro

In this paper, we initiate a rigorous study of the phenomenon of low-dimensional adversarial perturbations (LDAPs) in classification. Unlike the classical setting, these perturbations are limited to a subspace of dimension $k$ which is much…

Machine Learning · Statistics 2022-07-05 Elvis Dohmatob , Chuan Guo , Morgane Goibert

In this paper, we focus on learning a linear time-invariant (LTI) model with low-dimensional latent variables but high-dimensional observations. We provide an algorithm that recovers the high-dimensional features, i.e. column space of the…

Systems and Control · Electrical Eng. & Systems 2024-06-27 Yuyang Zhang , Shahriar Talebi , Na Li

Deep Neural Networks (DNNs) have recently achieved great success in many classification tasks. Unfortunately, they are vulnerable to adversarial attacks that generate adversarial examples with a small perturbation to fool DNN models,…

Machine Learning · Computer Science 2022-07-07 Xiaowei Zhou , Ivor W. Tsang , Jie Yin

Recently, there has been a large amount of work towards fooling deep-learning-based classifiers, particularly for images, via adversarial inputs that are visually similar to the benign examples. However, researchers usually use Lp-norm…

Computer Vision and Pattern Recognition · Computer Science 2021-02-02 Pengrui Quan , Ruiming Guo , Mani Srivastava

We propose an adversarial evaluation framework for sensitive feature inference based on minimum mean-squared error (MMSE) estimation with a finite sample size and linear predictive models. Our approach establishes theoretical lower bounds…

Machine Learning · Statistics 2025-05-15 Monica Welfert , Nathan Stromberg , Mario Diaz , Lalitha Sankar

We study a class of adversarial bandit optimization problems in which the loss functions may be non-convex and non-smooth. In each round, the learner observes a loss that consists of an underlying linear component together with an…

Machine Learning · Computer Science 2026-03-30 Zhuoyu Cheng , Kohei Hatano , Eiji Takimoto

Previous adversarial training raises model robustness under the compromise of accuracy on natural data. In this paper, we reduce natural accuracy degradation. We use the model logits from one clean model to guide learning of another one…

Computer Vision and Pattern Recognition · Computer Science 2021-08-17 Jiequan Cui , Shu Liu , Liwei Wang , Jiaya Jia

The existence of adversarial data examples has drawn significant attention in the deep-learning community; such data are seemingly minimally perturbed relative to the original data, but lead to very different outputs from a deep-learning…

Machine Learning · Computer Science 2019-11-12 Bai Li , Changyou Chen , Wenlin Wang , Lawrence Carin

Neural networks are not learning optimal decision boundaries. We show that decision boundaries are situated in areas of low training data density. They are impacted by few training samples which can easily lead to overfitting. We provide a…

Machine Learning · Computer Science 2023-10-09 Johannes Schneider

Estimating and optimizing Mutual Information (MI) is core to many problems in machine learning; however, bounding MI in high dimensions is challenging. To establish tractable and scalable objectives, recent work has turned to variational…

Machine Learning · Computer Science 2019-05-17 Ben Poole , Sherjil Ozair , Aaron van den Oord , Alexander A. Alemi , George Tucker

Analyzing large volumes of high-dimensional data is an issue of fundamental importance in data science, molecular simulations and beyond. Several approaches work on the assumption that the important content of a dataset belongs to a…

Machine Learning · Statistics 2018-03-20 Elena Facco , Maria d'Errico , Alex Rodriguez , Alessandro Laio