EdgeFool generates adversarial images to mislead classifiers.
problem Misleading classifiers with adversarial images.
method Trains a fully convolutional neural network to generate perturbations that enhance image details and mislead classifiers.
result EdgeFool outperforms other adversarial methods on various classifiers and datasets.
Paper shows softmax output misleads in evaluating adversarial example strength.
problem Softmax output misleads in evaluating adversarial example strength.
method Demonstrates how adversarial examples can exploit softmax properties.
result Softmax output is a poor indicator of adversarial example strength.
Method removes misleading data to improve ML model accuracy.
problem Unhealthy fear of missing out on data leads to model instability and poor performance.
method Bayesian sequential selection method that identifies and selects critical information.
result Improves sample-wise error convergence and eliminates model instabilities.
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.
problem Common confound removal methods in machine learning lead to misleading predictions.
method Featurewise removal of confound variance by linear regression before applying ML.
result This common deconfounding approach can leak information, amplifying null or moderate effects.
Crowdsourced algorithms identify fake news on Twitter.
problem Identifying fake news on social media platforms.
method Evaluation of reputation algorithms on a large dataset of Twitter news.
result Simple crowdsourcing-based algorithms can identify a significant portion of fake news with low false positive rates.
Google Trends can lead to misleading forecasts if not used carefully.
problem Misleading forecasts due to the variability of Google Trends data.
method Analyzing the variability of Google Trends data and proposing solutions.
result Google Trends can be a problem if not used with caution.
AXE evaluates explanations to avoid misleading Rashomon set model selection.
problem Evaluating explanations for Rashomon set models to avoid false selection.
method Proposed AXE method to evaluate explanation quality.
result AXE detects adversarial fairwashing with 100% success rate.
Feature selection from wide datasets leads to misleading results.
problem Feature selection in wide datasets with few samples can lead to misleading results.
method Derived sample size requirement for declaring features different, used real datasets to illustrate issues.
result Feature selection from very wide datasets may lead to misleading results.
A method for data encryption makes data look identical to humans but misleading to machine learning.
problem Data leakage in data sharing for medical purposes.
method Proposes a method inspired by adversarial attacks for data encryption.
result Encrypted data look identical to humans but misleading to machine learning methods.
Improves visualization of high-dimensional data by correcting misleading artifacts in neighbor embedding methods.
problem Misleading visual artifacts in t-SNE and UMAP due to lack of data-independent manifold learning interpretations.
method LOO-map framework that extends embedding maps to the entire input space, identifying and correcting map discontinuities.
result Developed point-wise diagnostic scores to detect unreliable embedding points and improve hyperparameter selection.
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…
Paper presents a code authorship attribution attack using adversarial learning.
problem Misleading attribution of source code using machine learning methods.
method Exploits adversarial examples and semantics-preserving code transformations guided by Monte-Carlo tree search.
result Demonstrates substantial effect on attribution methods, reducing accuracy from over 88% to 1%.
New research shows CI in few-shot learning is misleading due to sampling with replacement.
problem Misleading confidence intervals in few-shot learning due to sampling with replacement.
method Comparative analysis of CIs computed with and without replacement.
result Significant underestimation of CI by the predominant method.
New research highlights flaws in evaluating clustering algorithms using classification datasets.
problem Flaws in evaluating clustering algorithms using classification datasets.
method Advanced visualization and dimension reduction techniques to expose flaws.
result Current practice of evaluating clustering algorithms may produce misleading results.
The paper improves HER by prioritizing virtual goals and removing misleading samples.
problem Sparse reward functions in reinforcement learning.
method Prioritizing virtual goals based on instructiveness and removing misleading samples.
result Significant improvement in success rate and sample efficiency.
Proposes an active RBI framework using Rényi information measures for more informed decision-making.
problem Optimal latent variable estimates in real-time settings with streaming noisy observations.
method Unified inference and query selection steps through Rényi entropy and α-divergence; new objective called Momentum for exploration.
result Analytically demonstrates superior performance compared to conventional methods like mutual information.
GRACE-C improves causal learning from time series data.
problem Misleading causal information due to mismatched timescales.
method Combines constraint programming with theoretical insights and prior information.
result Significantly faster and scalable causal learning for large datasets.
MALCOM generates fake comments to fool fake news detectors.
problem Adversaries can manipulate fake news detection models with malicious comments.
method Proposes a novel threat model and develops an adversarial comment generation framework (MALCOM).
result MALCOM can fool fake news detectors 90-94% of the time, depending on the model and dataset.
ManiGen generates adversarial examples without classifier knowledge.
problem Vulnerability of neural network classifiers to adversarial examples.
method Generates adversarial examples by searching along the manifold.
result Adversarial examples generated by ManiGen are as successful as state-of-the-art generators.
Measures faithfulness of LLM explanations to reveal hidden biases and misleading claims.
problem LLM explanations can misrepresent the model's reasoning process, leading to over-trust and misuse.
method Defines faithfulness in terms of concept influence and uses counterfactuals and Bayesian models to estimate it.
result Can quantify and discover interpretable patterns of unfaithfulness in LLM explanations.
Detects adversarial examples with non-linear dimensionality reduction.
problem Vulnerability of deep neural networks to adversarial examples.
method Combining non-linear dimensionality reduction and density estimation.
result Effective detection of adversarial examples by non-adaptive attackers.
Knot Floer homology reveals fixed points of monodromy.
problem Understanding fixed points of monodromy for fibered knots.
method Knot Floer homology and monodromy analysis.
result Monodromy of a fibered knot has at most rank minus one fixed points.
Identifies feature relevance bounds for ordinal regression models.
problem Interpreting ordinal regression models is challenging due to variable dependencies.
method Identifies feature relevance bounds explicitly differentiating between strongly and weakly relevant features.
result Identification of feature relevance bounds for ordinal regression models.
T-BFA targets and misleads specific DNN inputs to a chosen output.
problem Targeted attack on DNN weight parameters to hijack function.
method Identifies critical weight bits, ranks them by class dependence, and flips them to mislead inputs.
result Successfully misclassifies images from 'Hen' to 'Goose' class with 100% success rate, maintaining 59.35% validation accuracy.
New study finds optimal hyperparameter tuning crucial for fair optimizer comparisons.
problem Inadequate hyperparameter tuning and misleading evaluation setups hinder fair comparisons of optimizers.
method Systematic study of ten optimizers across four model scales and data-to-model ratios.
result Optimal hyperparameters for one optimizer may be suboptimal for another, and many claimed speedups are lower than expected.
Experiments used in current continual learning research do not faithfully assess fundamental challenges of learning continually. Instead of assessing performance on challenging and representative experiment designs, recent research has focused on increased dataset difficulty, while still using flawed experiment set-ups…
Test log-likelihood comparisons can be misleading.
problem Misinterpretation of test log-likelihood in model comparison.
method Simple examples of model comparison and forecast accuracy.
result Test log-likelihood does not always correlate with model accuracy.
Adversarial trading samples hurt financial markets.
problem Impact of adversarial samples on financial markets.
method Implemented adversarial samples in a trading environment.
result Adversarial samples negatively impact certain market participants.
Proposes a simple solution to Gini importance bias in random forests.
problem Gini importance measure in random forests is biased and unreliable.
method Computes loss reduction on out-of-bag samples instead of in-bag.
result Solves the misleading/untrustworthy Gini importance issue.
Study compares uncertainty estimation methods for Bayesian Neural Networks.
problem Quality of uncertainty quantification in Bayesian Neural Networks.
method Empirical comparison of 10 inference methods on regression and classification tasks.
result Common inference metrics can be misleading, and methods designed to capture posterior structure do not always produce high-quality approximations.
The Fisher information approximation (FIA) is an implementation of the minimum description length principle for model selection. Unlike information criteria such as AIC or BIC, it has the advantage of taking the functional form of a model into account. Unfortunately, FIA can be misleading in finite samples, resulting i…
Exact spectral norm regularization improves neural network generalization.
problem Improving neural network generalization while protecting against noise.
method Exact spectral norm regularization of the Jacobian.
result Improved generalization performance compared to previous methods.
New method explains survival analysis models using median-SHAP.
problem Need for explainable AI in medical applications, especially for survival analysis.
method Introduces median-SHAP for explaining survival analysis models.
result Conventionally used mean anchor point can lead to misleading interpretations; median-SHAP provides a better approach.
New method tackles label noise on imbalanced datasets by considering class-specific uncertainty.
problem Label noise and class imbalance in imbalanced datasets.
method Epistemic and aleatoric uncertainty-aware class-specific noise modeling.
result Proposed ULC framework improves performance on imbalanced datasets.
Anti-transfer learning prevents misleading representations for speech tasks.
problem Misleading representations learned from orthogonal tasks in speech processing.
method Penalizes similarity between activations of a network and another trained on an orthogonal task.
result Improves classification accuracy and invariance to the orthogonal task.
Saliency methods aim to explain the predictions of deep neural networks. These methods lack reliability when the explanation is sensitive to factors that do not contribute to the model prediction. We use a simple and common pre-processing step ---adding a constant shift to the input data--- to show that a transformatio…
Value-at-Risk is a flawed substitute for non-ruin capital, leading to misleading financial standards.
problem Misuse of Value-at-Risk as a risk measure, replacing non-ruin capital, leads to flawed financial standards.
method Mathematical analysis of risk measures and their implications on financial standards.
result Non-ruin capital is a more accurate risk measure than Value-at-Risk, necessitating its adoption over the former.
The paper analyzes uncertainty quantification in sparse Gaussian process regression with a Brownian motion prior.
problem Analyzing uncertainty in sparse Gaussian process regression with a Brownian motion prior.
method Theoretical guarantees and limitations for pointwise credible sets are derived for a rescaled Brownian motion prior with a sparse variational Gaussian process method.
result Theoretical characterization of asymptotic frequentist coverage for credible sets, distinguishing conservative and overconfident cases.
Improves material discovery through better model evaluation metrics.
problem Standard error metrics mislead in material discovery.
method Introduces Pareto shell-scope error for model evaluation.
result Novel diagnostic tools and insights for acquisition function design.
Enhances investment performance by leveraging cross-market information.
problem Maximizing portfolio performance in asset markets with shared characteristics.
method Transfer learning applied to portfolio optimization.
result Achieves maximum Sharpe ratio asymptotically.
This article presents results from the first statistically significant study of cost escalation in transportation infrastructure projects. Based on a sample of 258 transportation infrastructure projects worth US$90 billion and representing different project types, geographical regions, and historical periods, it is fou…
Bayesian priors offer a compact yet general means of incorporating domain knowledge into many learning tasks. The correctness of the Bayesian analysis and inference, however, largely depends on accuracy and correctness of these priors. PAC-Bayesian methods overcome this problem by providing bounds that hold regardless …
Generative models use Riemannian manifolds to improve latent space interpretation.
problem Generative models often bias latent space interpretations.
method Use Riemannian manifolds to define latent space paths that respect ambient geometry.
result Improves interpretability of learned representations for both stochastic and deterministic generators.
With the advent of highly predictive but opaque deep learning models, it has become more important than ever to understand and explain the predictions of such models. Existing approaches define interpretability as the inverse of complexity and achieve interpretability at the cost of accuracy. This introduces a risk of …
Bayesian CNN estimates uncertainty in bone age prediction.
problem Uncertainty quantification in age estimation models.
method Variational Inference for Bayesian CNNs.
result Model uncertainty distinguished from data uncertainty.
We show that dropout training is best understood as performing MAP estimation concurrently for a family of conditional models whose objectives are themselves lower bounded by the original dropout objective. This discovery allows us to pick any model from this family after training, which leads to a substantial improvem…
It is well-known that intersection of continuous correspondences can lost the continuity property. Lechicki and Spakowski's theorem says that intersection of H-lsc functions remains H-lsc if the intersection is a bounded subset of a normed space and its interior is nonempty. Lechicki and Spakowski pointed to the import…