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.
Feature selection from wide datasets leads to misleading results.
T-BFA targets and misleads specific DNN inputs to a chosen output.
MALCOM generates fake comments to fool fake news detectors.
Even before deep learning architectures became the de facto models for complex computer vision tasks, the softmax function was, given its elegant properties, already used to analyze the predictions of feedforward neural networks. Nowadays, the output of the softmax function is also commonly used to assess the strength …
New method tackles label noise on imbalanced datasets by considering class-specific uncertainty.
This research analyzes how input and output layers affect deep neural networks' resistance to adversarial attacks.
In this paper, we analyze efficacy of the fast gradient sign method (FGSM) and the Carlini-Wagner's L2 (CW-L2) attack. We prove that, within a certain regime, the untargeted FGSM can fool any convolutional neural nets (CNNs) with ReLU activation; the targeted FGSM can mislead any CNNs with ReLU activation to classify a…
Exact spectral norm regularization improves neural network generalization.
Ensemble learning is a methodology that integrates multiple DNN learners for improving prediction performance of individual learners. Diversity is greater when the errors of the ensemble prediction is more uniformly distributed. Greater diversity is highly correlated with the increase in ensemble accuracy. Another attr…
Topic models are Bayesian models that are frequently used to capture the latent structure of certain corpora of documents or images. Each data element in such a corpus (for instance each item in a collection of scientific articles) is regarded as a convex combination of a small number of vectors corresponding to `topic…
Deep neural networks (DNNs) have shown huge superiority over humans in image recognition, speech processing, autonomous vehicles and medical diagnosis. However, recent studies indicate that DNNs are vulnerable to adversarial examples (AEs), which are designed by attackers to fool deep learning models. Different from re…
Method removes misleading data to improve ML model accuracy.
We analyse an issue when comparing survival curves between two subgroups. We show that there is a direct relationship between estimates of subgroups' survival at a time point and positive and negative predictive values in the binary classification settings. Our findings present a case where current methods of comparing…
Machine learning confound removal biases results, leading to misleading predictions.
Social networks offer a ready channel for fake and misleading news to spread and exert influence. This paper examines the performance of different reputation algorithms when applied to a large and statistically significant portion of the news that are spread via Twitter. Our main result is that simple crowdsourcing-bas…
The safety and robustness of learning-based decision-making systems are under threats from adversarial examples, as imperceptible perturbations can mislead neural networks to completely different outputs. In this paper, we present an adaptive view of the issue via evaluating various test-time smoothing defense against …
Deep neural networks (DNNs) are vulnerable to subtle adversarial perturbations applied to the input. These adversarial perturbations, though imperceptible, can easily mislead the DNN. In this work, we take a control theoretic approach to the problem of robustness in DNNs. We treat each individual layer of the DNN as a …
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
Saliency methods have emerged as a popular tool to highlight features in an input deemed relevant for the prediction of a learned model. Several saliency methods have been proposed, often guided by visual appeal on image data. In this work, we propose an actionable methodology to evaluate what kinds of explanations a g…
Perfect adaptation in systems is identified and tested using graphical tools.
Google Trends can lead to misleading forecasts if not used carefully.
AXE evaluates explanations to avoid misleading Rashomon set model selection.
Adversarial examples are intentionally perturbed images that mislead classifiers. These images can, however, be easily detected using denoising algorithms, when high-frequency spatial perturbations are used, or can be noticed by humans, when perturbations are large. In this paper, we propose EdgeFool, an adversarial im…
Machine learning models are vulnerable to simple model stealing attacks if the adversary can obtain output labels for chosen inputs. To protect against these attacks, it has been proposed to limit the information provided to the adversary by omitting probability scores, significantly impacting the utility of the provid…
A method for data encryption makes data look identical to humans but misleading to machine learning.
In this paper, we present a novel attack against authorship attribution of source code. We exploit that recent attribution methods rest on machine learning and thus can be deceived by adversarial examples of source code. Our attack performs a series of semantics-preserving code transformations that mislead learning-bas…
CROP verifies clean prefixes in reasoning traces, improving downstream repair accuracy.
Popular deep learning uncertainty estimation methods often mislead on out-of-distribution data.
We study empirical covariance matrices in finance. Due to the limited amount of available input information, these objects incorporate a huge amount of noise, so their naive use in optimization procedures, such as portfolio selection, may be misleading. In this paper we investigate a recently introduced filtering proce…
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
We investigate task clustering for deep-learning based multi-task and few-shot learning in a many-task setting. We propose a new method to measure task similarities with cross-task transfer performance matrix for the deep learning scenario. Although this matrix provides us critical information regarding similarity betw…
New research shows CI in few-shot learning is misleading due to sampling with replacement.
Paper proposes forecast-necessity testing for accurate causal interpretation in nonlinear time-series models.
XAI methods often misattribute importance to suppressor variables, limiting their reliability.
Interactive tool for better understanding t-SNE projections.
Backdoor attacks make models predict a specific class near triggers, smoothing their decision function.
This paper reviews and advocates against the use of permute-and-predict (PaP) methods for interpreting black box functions. Methods such as the variable importance measures proposed for random forests, partial dependence plots, and individual conditional expectation plots remain popular because they are both model-agno…
Proposes an active RBI framework using Rényi information measures for more informed decision-making.
Deep neural networks are vulnerable to adversarial examples, i.e., carefully-perturbed inputs aimed to mislead classification. This work proposes a detection method based on combining non-linear dimensionality reduction and density estimation techniques. Our empirical findings show that the proposed approach is able to…
GRACE-C improves causal learning from time series data.
ManiGen generates adversarial examples without classifier knowledge.
Proposes ICE-based metric for better understanding interactions in black-box models.
Bayesian Neural Networks (BNNs) place priors over the parameters in a neural network. Inference in BNNs, however, is difficult; all inference methods for BNNs are approximate. In this work, we empirically compare the quality of predictive uncertainty estimates for 10 common inference methods on both regression and clas…
The increasing occurrence of ordinal data, mainly sociodemographic, led to a renewed research interest in ordinal regression, i.e. the prediction of ordered classes. Besides model accuracy, the interpretation of these models itself is of high relevance, and existing approaches therefore enforce e.g. model sparsity. For…
This paper uses Gaussian processes to forecast short-term stock price volatility.
Adversarial examples are delicately perturbed inputs, which aim to mislead machine learning models towards incorrect outputs. While most of the existing work focuses on generating adversarial perturbations in multi-class classification problems, many real-world applications fall into the multi-label setting in which on…
Measures faithfulness of LLM explanations to reveal hidden biases and misleading claims.
Task loss matching misrepresents similarity between neural network layers.