Batch normalization shifts models to rely more on non-robust features.
problem Understanding the impact of batch normalization on deep neural networks.
method Empirical analysis and a framework for disentangling robustness and usefulness.
result Batch normalization increases reliance on non-robust features, decreasing adversarial robustness.
AAT separates robust and non-robust features without supervision.
problem Adversarial vulnerability and accuracy reduction in machine learning models.
method Adversarial Asymmetric Training (AAT) algorithm.
result Preserves accuracy and achieves better disentanglement than previous methods.
Given the apparent difficulty of learning models that are robust to adversarial perturbations, we propose tackling the simpler problem of developing adversarially robust features. Specifically, given a dataset and metric of interest, the goal is to return a function (or multiple functions) that 1) is robust to adversar…
Unified analysis of removal-based feature attributions robustness.
problem Robustness of removal-based feature attributions is not well understood.
method Theoretical analysis and upper bounds derivation for removal-based feature attributions under input and model perturbations.
result Upper bounds for the difference between intact and perturbed attributions derived under various perturbation settings.
BN helps learn fragile features, which can improve adversarial robustness.
problem The role of batch normalization in adversarial training and its impact on robustness.
method Investigated the expressiveness of BN in learning robust features compared to random features.
result Adversarially fine-tuning BN layers can result in non-trivial adversarial robustness.
RAEUFS selects features from data without labels, improving robustness to outliers.
problem Feature selection in high-dimensional data, especially in the presence of outliers.
method RAEUFS uses a deep autoencoder to learn nonlinear feature representations, improving robustness to outliers.
result RAEUFS outperforms state-of-the-art UFS methods in both clean and outlier-contaminated data settings.
Gradient descent biases neural networks to use an average of features, leading to non-robustness.
problem Non-robustness in neural networks due to feature averaging.
method Theoretical analysis and experiments on binary classification tasks.
result Gradient descent trains networks to rely on an average of features, making them vulnerable to adversarial attacks.
In recent years, it has been found that neural networks can be easily fooled by adversarial examples, which is a potential safety hazard in some safety-critical applications. Many researchers have proposed various method to make neural networks more robust to white-box adversarial attacks, but an effective method have …
Robust feature-weighted jump models for time-dependent clustering
problem Temporal clustering
method Robust feature-weighted jump model
result Accurate recovery of true cluster sequence and feature identification
Adversarial training has been successfully applied to build robust models at a certain cost. While the robustness of a model increases, the standard classification accuracy declines. This phenomenon is suggested to be an inherent trade-off. We propose a model that employs feature prioritization by a nonlinear attention…
New framework learns sufficient invariant features robustly across distribution shifts.
problem Learning robust models under distribution shifts between training and test datasets.
method Sufficient Invariant Learning (SIL) framework and Adaptive Sharpness-aware Group Distributionally Robust Optimization (ASGDRO) algorithm.
result Empirical evaluations confirm ASGDRO's robustness against distribution shifts.
A new method transfers adversarial robustness from teacher to student using feature distillation.
problem Adversarial robustness transfer across different models and tasks.
method Guided Adversarial Contrastive Distillation (GACD) with contrastive learning and sample reweighted estimation.
result GACD effectively transfers adversarial robustness from teacher to student, achieving comparable or better results.
We propose a novel strategy for extracting features in supervised learning that can be used to construct a classifier which is more robust to small perturbations in the input space. Our method builds upon the idea of the information bottleneck by introducing an additional penalty term that encourages the Fisher informa…
Paper introduces robust learning from feature feedback, even with annotator errors.
problem Learning from human feedback on discriminative features, especially when annotators make mistakes.
method Develops a robust framework for learning with imperfect feedback, deriving regret bounds in adversarial and stochastic settings.
result Regret bounds independent of feature number, showing robust learning is not reducible to non-robust settings.
Existing deep neural networks, say for image classification, have been shown to be vulnerable to adversarial images that can cause a DNN misclassification, without any perceptible change to an image. In this work, we propose shock absorbing robust features such as binarization, e.g., rounding, and group extraction, e.g…
RTFE provides adversarial robustness to multiple models.
problem Adversarial examples can transfer to other models, compromising robustness.
method Proposes RTFE, a deep learning-based pre-processing mechanism.
result RTFE provides adversarial robustness to multiple independently trained classifiers.
CLIP models robustness to spurious features is re-evaluated using a new dataset.
problem Existing robustness tests of CLIP models may not fully reflect their performance on spurious features.
method Crafted a new dataset (CounterAnimal) to reveal CLIP models' reliance on realistic spurious features.
result CLIP models are robust to spurious features learned from their training data, not ImageNet.
Study robustness of global feature effect explanations in machine learning models.
problem Vulnerability of global feature effect explanations to data and model perturbations.
method Theoretical bounds and experimental evaluation of partial dependence plots and accumulated local effects.
result Quantifies the gap between best and worst-case scenarios of misinterpreting machine learning predictions globally.
New approach to adversarial robustness with non-uniform perturbations.
problem Real-world adversaries craft adversarial examples with non-uniform perturbations.
method Proposes non-uniform perturbations based on feature dependencies and data distribution.
result Shows improved robustness to real-world attacks compared to uniform perturbations.
New robust algorithms improve learning with feature feedback.
problem Interactive learning with discriminative feature feedback.
method Developed new robust interactive learning algorithms with improved mistake bounds.
result Achieved significantly lower mistake bounds in adversarial and stochastic settings.
We consider the problem of learning linear classifiers when both features and labels are binary. In addition, the features are noisy, i.e., they could be flipped with an unknown probability. In Sy-De attribute noise model, where all features could be noisy together with same probability, we show that 0-1 loss ($l_{…
RoSHAP stabilizes feature attribution in machine learning models.
problem Stochastic variation in feature attribution measures.
method Modeling feature attribution score distribution and estimating it through bootstrap resampling and kernel density estimation.
result RoSHAP provides stable feature rankings and improves model performance.
Adversarial robustness in multi-index models is as easy as standard learning.
problem Adversarial robustness in high-dimensional multi-index models.
method Proves that hidden directions of multi-index models offer a Bayes optimal low-dimensional projection for robustness against ℓ2-bounded adversarial perturbations. result Adversarially robust learning is as easy as standard learning, requiring no additional samples.
Paper quantifies label shift with robustness guarantees using distribution feature matching.
problem Estimating target label distribution under label shift.
method Distribution feature matching (DFM) framework and robustness analysis.
result General performance bound and robustness analysis in misspecified settings.
RTFN extracts robust temporal features for time series analysis.
problem Challenges in extracting sufficient shapelets from time series data.
method Combines temporal feature networks and attentional LSTM networks.
result RTFN outperforms in supervised and unsupervised time series analysis.
Paper develops robust k-NN algorithm for few samples.
problem Learning robust classifier from limited samples.
method Distributionally robust formulation of weighted k-NN. result Robust classifier improves generalization with smaller Lipschitz norm.
Paper introduces new evaluation criteria for feature-based model explanations.
problem Establishing reliable feature importance explanations for models.
method Robustness analysis using smaller adversarial perturbations.
result New explanations that are necessary and sufficient for predictions.
Adding node feature kernels improves GCN robustness to graph perturbations.
problem GCNs' robustness to graph perturbations is a concern.
method Introduced random GCN and added node feature kernels to message passing.
result Perturbations of the graph structure can significantly degrade GCN performance.
CTRF combines logged data and randomized experiments for robust prediction.
problem Robust prediction models to handle distributional shifts between training and testing data.
method CTRF uses existing training data and a small amount of randomized experiment data to train a robust model.
result CTRF produces robust predictions and outperforms baseline methods in the presence of feature shifts.
Safe-DRFS selects features robust to covariate shifts for reliable performance.
problem Feature selection fails in diverse deployment environments.
method Safe-DRFS extends safe screening to distributionally robust settings under covariate shift.
result Safe-DRFS identifies a feature subset encompassing optimal subsets across distribution shifts.
Paper develops robust SVM classifiers for uncertain data.
problem Sensitivity of SVM classifiers to data uncertainty.
method Two probabilistic approaches: Single Perturbation and Extreme Empirical Loss.
result Both methods reduce data uncertainty effects efficiently.
A new method for feature selection robust to noise and design variability.
problem Feature selection in high-dimensional regression under sampling variability and measurement error.
method Injects controlled additive noise into the design matrix, fits a base selector, and aggregates selection frequencies.
result Improved robustness compared to Stability Selection and standard base selectors.
GRIP2 improves deep learning feature selection robustness in correlated and noisy data.
problem Identifying predictive features in correlated and noisy data.
method Integrates first-layer feature activity over a two-dimensional regularization surface to control sparsity and geometry, using efficient block-stochastic sampling.
result Demonstrates improved robustness and power in high correlation and low signal-to-noise ratio regimes.
A new method improves adversarial robustness and interpretability with reduced training time.
problem Adversarial attacks on deep neural networks.
method A novel regularizer incorporating first and second order information via a quadratic approximation to the adversarial loss.
result Single iteration of the proposed regularizer achieves stronger robustness than prior methods.
Conformal prediction fails under severe feature turnover in COVID-19 supply chain tasks.
problem Dealing with distribution shift in conformal prediction models.
method Using COVID-19 as a natural experiment across 8 supply chain tasks, analyzing SHAP explanations.
result Coverage drops vary widely (0% to 86.7%) and correlate with single-feature dependence.
Algorithm identifies and transfers unstable features to create robust classifiers.
problem Developing unbiased classifiers from input-label pairs alone.
method Contrast different data environments in source tasks to encode unstable features, then cluster target task data and minimize worst-case risk.
result Our method maintains robustness across synthetic and real-world environments.
Removing spurious features can hurt model accuracy and disproportionately affect different groups.
problem Interference from spurious features in robust model performance across different groups.
method Characterization and analysis of spurious feature removal in noiseless overparameterized linear regression.
result Removal of spurious features can decrease accuracy and disproportionately affect different groups, even in balanced datasets.
TAROT enhances robustness and domain adaptability with domain-invariant features.
problem Developing models robust to adversarial attacks across diverse domains.
method Derives a new generalization bound and proposes TAROT algorithm.
result TAROT outperforms state-of-the-art methods in accuracy and robustness.
ClusTR improves clustering-based models' robustness without adversarial training.
problem Improving clustering-based models' robustness.
method Proposes ClusTR, a clustering-based training framework for robust models without adversarial training.
result ClusTR outperforms adversarially-trained models by up to 4% under strong PGD attacks.
Adapts IG for better feature attributions and robustness.
problem Reliability concerns in feature attributions for deep learning models.
method Adaptation of path-based feature attribution to Riemannian geometry of data manifolds.
result IG along geodesics generates more intuitive and robust explanations.
Enhances deep learning robustness to noise without sacrificing clean data accuracy.
problem Robustness of deep neural networks to input noise.
method Discriminative loss at penultimate layer and class-wise feature alignment with Gaussian noise.
result Improves robustness to various perturbations without degrading clean data accuracy.
We investigate the effect of the dimensionality of the representations learned in Deep Neural Networks (DNNs) on their robustness to input perturbations, both adversarial and random. To achieve low dimensionality of learned representations, we propose an easy-to-use, end-to-end trainable, low-rank regularizer (LR) that…
New insights into model robustness for random features and NTK models.
problem Understanding and distinguishing robustness in machine learning models.
method Analyzing empirical risk minimization in random features and NTK models.
result Random features models are not robust under any degree of over-parameterization, even when satisfying the universal law of robustness.
Paper tackles robust decision-making from multiple sites with shared structure.
problem Learning robust sequential decisions from heterogeneous multi-site datasets.
method Group-Robust MDPs with d-rectangular uncertainty sets, feature-wise worst-case aggregation, and cluster-level pooling.
result Proves suboptimality bound for robust planning policy under robust partial coverage assumption.
AugLoss combines data augmentation and robust loss functions for robust DL models.
problem Robustness against noisy labels and feature distribution shifts.
method Unified data augmentation and robust loss functions.
result AugLoss achieves gains over previous methods in various real-world dataset corruptions.
An important goal in deep learning is to learn versatile, high-level feature representations of input data. However, standard networks' representations seem to possess shortcomings that, as we illustrate, prevent them from fully realizing this goal. In this work, we show that robust optimization can be re-cast as a too…
AFD learns features resistant to adversarial attacks.
problem Vulnerability of neural networks to adversarial attacks.
method AFD learns features invariant to adversarial perturbations through a game of predictive and robust features.
result AFD effectively resists a wide range of attack types and strengths.
This paper introduces LR-FFS for robust feature screening in federated learning under label shift.
problem Label shift challenges in federated learning for high-dimensional classification.
method Unified feature screening framework, label-shift robust federated feature screening (LR-FFS), federated estimation procedure.
result LR-FFS outperforms existing methods in diverse client environments with varying class distributions, sample sizes, and missing data.