A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
Paper identifies classes vulnerable to adversarial attacks.
A susceptibility propagation that is constructed by combining a belief propagation and a linear response method is used for approximate computation for Markov random fields. Herein, we formulate a new, improved susceptibility propagation by using the concept of a diagonal matching method that is based on mean-field app…
Quantitative susceptibility mapping (QSM) is a powerful MRI technique that has shown great potential in quantifying tissue susceptibility in numerous neurological disorders. However, the intrinsic ill-posed dipole inversion problem greatly affects the accuracy of the susceptibility map. We propose QSMGAN: a 3D deep con…
Overparameterized linear model shows strong classification but weak regression, susceptible to adversarial perturbations.
CycleQSM uses deep learning to accurately map tissue magnetic susceptibility without needing paired data.
New method bounds membership inference attack success using mutual information.
SmoothFool efficiently computes smooth adversarial perturbations for deep networks.
A classic problem with intriguing implications at the level of both applied differential geometry and theoretical physics is dealt with in this short work: Is there any criterion in order to decide whether a pseudo-Riemannian space can be locally described using curvature scalars solely? Surprisingly enough, this quest…
Graph filtering reduces intra-class noise for improved classification accuracy.
NDI enables high-quality QSM without parameter tuning.
Machine learning predicts flood risk across river basins.
Although many convex relaxations of clustering have been proposed in the past decade, current formulations remain restricted to spherical Gaussian or discriminative models and are susceptible to imbalanced clusters. To address these shortcomings, we propose a new class of convex relaxations that can be flexibly applied…
A wide range of defenses have been proposed to harden neural networks against adversarial attacks. However, a pattern has emerged in which the majority of adversarial defenses are quickly broken by new attacks. Given the lack of success at generating robust defenses, we are led to ask a fundamental question: Are advers…
Softmax and k-means clustering are mathematically linked, improving neural network robustness.
Developments in deep generative models have allowed for tractable learning of high-dimensional data distributions. While the employed learning procedures typically assume that training data is drawn i.i.d. from the distribution of interest, it may be desirable to model distinct distributions which are observed sequenti…
SSMs can be poisoned with clean labels, leading to generalization failure.
We approach the development of models and control strategies of susceptible-infected-susceptible (SIS) epidemic processes from the perspective of marked temporal point processes and stochastic optimal control of stochastic differential equations (SDEs) with jumps. In contrast to previous work, this novel perspective is…
Study prenatal PM2.5 exposure and 4th grade reading scores, identifying critical windows of susceptibility.
Despite the wide use of machine learning in adversarial settings including computer security, recent studies have demonstrated vulnerabilities to evasion attacks---carefully crafted adversarial samples that closely resemble legitimate instances, but cause misclassification. In this paper, we examine the adequacy of the…
Advanced inference techniques allow one to reconstruct the pattern of interaction from high dimensional data sets. We focus here on the statistical properties of inferred models and argue that inference procedures are likely to yield models which are close to a phase transition. On one side, we show that the reparamete…
In this paper, a unified susceptible-exposed-infected-susceptible-aware (SEIS-A) framework is proposed to combine epidemic spreading with individuals' on-line self-consultation behaviors. An epidemic spreading prediction model is established based on the SEIS-A framework. The prediction process contains two phases. In …
Paper introduces a new optimization method for imbalanced datasets.
Convolutional neural networks (CNNs) are known for their good performance and generalization in vision-related tasks and have become state-of-the-art in both application and research-based domains. However, just like other neural network models, they suffer from a susceptibility to noise and adversarial attacks. An adv…
Symmetrizes loss functions to improve neural network robustness against noisy labels.
Adversarial attacks and the development of (deep) neural networks robust against them are currently two widely researched topics. The robustness of Learning Vector Quantization (LVQ) models against adversarial attacks has however not yet been studied to the same extent. We therefore present an extensive evaluation of t…
Valid certifies LLMs' domain adherence, bounding out-of-domain behavior.
There is great potential for damage from adversarial learning (AL) attacks on machine-learning based systems. In this paper, we provide a contemporary survey of AL, focused particularly on defenses against attacks on statistical classifiers. After introducing relevant terminology and the goals and range of possible kno…
Neural networks improve cancer risk prediction from family history data.
Proposes a deep learning method for robust ordinal regression under label noise.
Adversarial attacks can fool copyright detection systems.
The kernel null-space technique and its regression-based formulation (called one-class kernel spectral regression, a.k.a. OC-KSR) is known to be an effective and computationally attractive one-class classification framework. Despite its outstanding performance, the applicability of kernel null-space method is limited d…
VampPrior Mixture Model improves clustering in DLVMs.
Deep learning classifies corn hybrids' tolerance to drought and heat.
Radio frequency (RF) sensors are used alongside other sensing modalities to provide rich representations of the world. Given the high variability of complex-valued target responses, RF systems are susceptible to attacks masking true target characteristics from accurate identification. In this work, we evaluate differen…
In this note we study logarithmic transformations in the sense of differential topology on two fibers of the Hopf surface. It is known that such transformations are susceptible to yield exotic smooth structures on four-manifolds. We will show here that this is not the case for the Hopf surface, all integer homology Hop…
Alternative hypothesis tests for class-conditional noise using local maximum likelihood.
Gradient-based methods can be biased by distributional asymmetries in bivariate categorical data.
Dynamic treatment strategies on networks amplify policy impact through spillovers.
A new algorithm improves GAN training stability and performance.
Note that this paper is superceded by "Black-Box Adversarial Attacks with Limited Queries and Information." Current neural network-based image classifiers are susceptible to adversarial examples, even in the black-box setting, where the attacker is limited to query access without access to gradients. Previous methods -…
LangDA improves domain adaptation for semantic segmentation by learning context-aware scene descriptions.
New method generates realistic adversarial images with smaller perturbations.
Localized uncertainty attacks target uncertain regions to create imperceptible adversarial examples.
In Machine Learning, ensemble methods have been receiving a great deal of attention. Techniques such as Bagging and Boosting have been successfully applied to a variety of problems. Nevertheless, such techniques are still susceptible to the effects of noise and outliers in the training data. We propose a new method for…
Several recent papers have discussed utilizing Lipschitz constants to limit the susceptibility of neural networks to adversarial examples. We analyze recently proposed methods for computing the Lipschitz constant. We show that the Lipschitz constant may indeed enable adversarially robust neural networks. However, the m…
Paper presents a statistical method for detecting adversarial inputs.
Study examines adversarial robustness of ANN variants, revealing differences in black-box settings.
Tensor network decomposition, originated from quantum physics to model entangled many-particle quantum systems, turns out to be a promising mathematical technique to efficiently represent and process big data in parsimonious manner. In this study, we show that tensor networks can systematically partition structured dat…