arXiv research

Study reveals how high-dimensional models are vulnerable to consistent adversarial attacks.

After Fossas-Parlier, we consider two graphs $\mathcal{G}_{0}(S)$ and $\mathcal{G}_{\infty}(S)$, constructed from multicurves on connected, orientable surfaces of infinite-type. Our first result asserts that $\mathcal{G}_{\infty}(S)$ has finite diameter, which extends a result of Fossas-Parlier. Next, we prove that the…

A fast method for discrete OT with group-sparse regularization for class label preservation.

The generation of artificial data based on existing observations, known as data augmentation, is a technique used in machine learning to improve model accuracy, generalisation, and to control overfitting. Augmentor is a software package, available in both Python and Julia versions, that provides a high level API for th…

This paper explores a variety of models for frame-based music transcription, with an emphasis on the methods needed to reach state-of-the-art on human recordings. The translation-invariant network discussed in this paper, which combines a traditional filterbank with a convolutional neural network, was the top-performin…

Deep artificial neural networks require a large corpus of training data in order to effectively learn, where collection of such training data is often expensive and laborious. Data augmentation overcomes this issue by artificially inflating the training set with label preserving transformations. Recently there has been…

A new method resolves non-identifiability in reward modeling using anchor labels.

Paper develops heavy-tailed embeddings for better text classification and augmentation.

Enhances data augmentation for regression tasks.

Regularising for invariance to data augmentation improves machine learning models.

Paper improves bike-sharing demand prediction by adapting to changing patterns.

In recent years, deep learning has achieved remarkable achievements in many fields, including computer vision, natural language processing, speech recognition and others. Adequate training data is the key to ensure the effectiveness of the deep models. However, obtaining valid data requires a lot of time and labor reso…

Earth observation embeddings can convert discrete biome maps into continuous representations that better capture ecological variation.

This paper presents a new approach, called perturb-max, for high-dimensional statistical inference that is based on applying random perturbations followed by optimization. This framework injects randomness to maximum a-posteriori (MAP) predictors by randomly perturbing the potential function for the input. A classic re…

The paper tackles extrapolation of gene knockouts effects on RNA counts.

Novel geometry-informed irreversible perturbation accelerates Langevin dynamics convergence.

Study linear perturbations in Schwarzschild black hole spacetime.

New research evaluates various perturbation methods for improving neural network robustness.

Convolutional neural networks (CNN) have become one of the most popular machine learning tools and are being applied in various tasks, however, CNN models are vulnerable to universal perturbations, which are usually human-imperceptible but can cause natural images to be misclassified with high probability. One of the s…

We study the transfer of adversarial robustness of deep neural networks between different perturbation types. While most work on adversarial examples has focused on $L_\infty$ and $L_2$-bounded perturbations, these do not capture all types of perturbations available to an adversary. The present work evaluates 32 attack…

EVILL uses randomised perturbations to improve exploration in bandit problems.

New bifurcation found in perturbations of non-generic closed self-shrinkers.

Adversarial perturbations fool deepfake detectors with high accuracy.

Advances FTPL results for bandit problems with unbounded perturbations.

Generative Intervention Models predict perturbation effects without knowing the underlying mechanisms.

Identifies all perturbative vacua in bosonic string theory.

Develops new methods to create imperceptible image changes that fool classifiers.

Charge measurements for instantons and gravitational perturbations.

Eigenvalues of Steklov eigenproblems change predictably with boundary tweaks.

Study linear perturbations of Spin(7) metrics, finding only rank one nilpotent matrices.

Simple perturbation of Vafa-Witten equations leads to transversality.

We developed a perturbation model for affine gravity theories.

Classifiers such as deep neural networks have been shown to be vulnerable against adversarial perturbations on problems with high-dimensional input space. While adversarial training improves the robustness of image classifiers against such adversarial perturbations, it leaves them sensitive to perturbations on a non-ne…

DBPA assesses LLM perturbations using frequentist hypothesis testing.

The paper learns perturbation sets from data to improve robustness in machine learning.

A fast method computes class-specific adversarial perturbations for deep networks.

Adversarial training, in which a network is trained on both adversarial and clean examples, is one of the most trusted defense methods against adversarial attacks. However, there are three major practical difficulties in implementing and deploying this method - expensive in terms of extra memory and computation costs; …

Study metric perturbations to make degenerate harmonic forms non-degenerate.

The paper proves new theorems about specific types of operator perturbations.

Given a state-of-the-art deep neural network text classifier, we show the existence of a universal and very small perturbation vector (in the embedding space) that causes natural text to be misclassified with high probability. Unlike images on which a single fixed-size adversarial perturbation can be found, text is of …

In this paper we investigate the usage of adversarial perturbations for the purpose of privacy from human perception and model (machine) based detection. We employ adversarial perturbations for obfuscating certain variables in raw data while preserving the rest. Current adversarial perturbation methods are used for dat…

The study reveals how adversarial perturbations can include class features for generalization.

Deep networks have recently been shown to be vulnerable to universal perturbations: there exist very small image-agnostic perturbations that cause most natural images to be misclassified by such classifiers. In this paper, we propose the first quantitative analysis of the robustness of classifiers to universal perturba…

Improved online Lasso reduces regret in sparse linear contextual bandits.

New method $μP^2$ improves neural network training by scaling perturbations layerwise.

Paper proposes a method to generate adversarial perturbations for black-box attacks without accessing inner states.

Deep neural networks are susceptible to adversarial manipulations in the input domain. The extent of vulnerability has been explored intensively in cases of $\ell_p$-bounded and $\ell_p$-minimal adversarial perturbations. However, the vulnerability of DNNs to adversarial perturbations with specific statistical properti…

New metric scores perturbations across populations, not cells, improving model comparison.