Develops a model-robust method for predicting counterfactual outcomes.
problem Quantifying the impact of different exposures on counterfactual outcomes.
method Uses prediction intervals based on conformal prediction for model-robust and distribution-free analysis.
result Demonstrates the effectiveness of the method using real and synthetic data.
The paper improves model robustness by regularizing posterior differences.
problem Improving model robustness in noisy input scenarios.
method Posterior differential regularization with f-divergence. result Regularizing with f-divergence improves model robustness. Wider networks improve natural accuracy but worsen perturbation stability, affecting overall robustness.
problem Understanding the tradeoff between natural accuracy and perturbation stability in wider neural networks for adversarial robustness.
method Careful examination of the relationship between network width, robust regularization parameter λ, and perturbation stability using neural tangent kernels.
result Wider networks can achieve better natural accuracy but worse perturbation stability, leading to potentially worse overall model robustness.
CEB enhances model resilience through simple entropy bottleneck.
problem Improving model robustness against adversarial attacks.
method Conditional Entropy Bottleneck (CEB) combined with data augmentation.
result CEB significantly boosts adversarial robustness on various benchmarks.
Self-supervised learning enhances model robustness and uncertainty.
problem Improving model robustness and uncertainty estimation.
method Self-supervised learning without requiring labels.
result Self-supervised learning improves robustness to adversarial examples, label corruption, and input corruptions.
ETs improve model robustness to transformations in images.
problem Improving model robustness to predefined transformations.
method Equivariant Transformers (ETs) incorporating functions equivariant to continuous transformation groups.
result ETs achieve up to 15% relative improvement in error rate on image classification tasks.
Study quantifies distribution shifts and uncertainties to improve machine learning model robustness.
problem Distribution shifts between training and test datasets impact model generalization and robustness.
method Synthetic data generation and quantitative measures (KL divergence, JS distance, Mahalanobis distance) to assess data similarity and model uncertainty.
result Utilizing statistical measures like Mahalanobis distance helps assess distribution shift and model uncertainty.
NoisyMix boosts model robustness to common corruptions.
problem Improving robustness of neural networks in real-world applications.
method NoisyMix training scheme that uses noisy augmentations in input and feature space.
result NoisyMix produces more robust models with well-calibrated class membership probabilities.
Pre-training improves model robustness and uncertainty.
problem Improving model robustness and uncertainty in machine learning.
method Adversarial pre-training and task-specific methods.
result Approximately a 10% absolute improvement in adversarial robustness.
New method improves model robustness against adversarial examples.
problem Tackles model robustness against adversarial examples.
method Exploits energy function to describe stability and minimizes lower bound of energy function.
result Proves better robustness than previous methods.
The paper assesses machine learning robustness with covariate perturbations.
problem Ensuring robustness of machine learning models against adversarial attacks and data changes.
method Proposes a framework using covariate perturbation techniques to assess model robustness.
result Demonstrates the effectiveness of the approach in comparing robustness across models and identifying instabilities.
New method improves adversarial training efficiency and robustness.
problem High computational costs and lack of stability in adversarial training.
method Backward smoothing for randomized smoothing of random initialization.
result Our method achieves similar model robustness as state-of-the-art methods but with significantly less training time.
Improves deep learning models' robustness with reverse adversarial examples.
problem Deep learning models' fragility to adversarial examples.
method Inspired by brain mechanisms, proposes reverse adversarial examples method.
result Average 19.02% accuracy improvement on unseen data transformation.
Noisy Feature Mixup improves model robustness with noise-perturbed convex combinations.
problem Improving model robustness against data perturbations.
method Noise-perturbed convex combinations of pairs of data points in input and feature space.
result Improved model robustness and favorable trade-offs between accuracy and robustness.
Transfer learning improves model robustness against adversarial attacks.
problem Understanding how transfer learning affects model robustness against adversarial attacks.
method Extensive empirical evaluations of white-box and black-box attacks on fine-tuned transfer learning models.
result Adversarial examples are more transferable when fine-tuning is used than when networks are trained independently.
The paper shows how causal knowledge improves model robustness.
problem Improving model robustness in the face of unseen domains.
method Utilizes Structural Causal Models (SCM) to guide model selection based on likelihood of the SCM given predictions and input variables.
result Identifies more robust models that generalize better to unseen domains.
Study makes code models robust to small changes that keep functionality.
problem Vulnerability of deep neural networks to adversarial examples in source code.
method Defined a powerful adversary and adversarial training to learn robust models.
result Significant gains in robustness demonstrated across different languages and architectures.
OC-BNNs enforce output constraints in BNNs, improving model robustness.
problem Hard to encode prior knowledge in function space for BNNs.
method Formulate a prior that incorporates functional constraints on output.
result OC-BNNs improve model robustness and prevent infeasible predictions.
The paper introduces boundary thickness as a measure for improving model robustness.
problem Improving the robustness of machine learning models to adversarial and non-adversarial corruptions.
method Introducing boundary thickness as a measure and showing how various procedures can increase it.
result Thicker decision boundaries lead to improved robustness against adversarial and out-of-distribution transforms.
New algorithm improves deep learning models' robustness without sacrificing accuracy.
problem Low-rank methods compromise model robustness against adversarial perturbations.
method Robust low-rank training via approximate orthonormal constraints.
result Ensures well-conditioning and better adversarial robustness without sacrificing model accuracy.
Improved model robustness against corruptions using online adaptation.
problem Machine vision models' vulnerability to image corruptions like blurring or compression artefacts.
method Using corrupted images' statistics for unsupervised online adaptation to improve robustness.
result ResNet-50 achieves 62.2% mCE on ImageNet-C with adaptation, improving from 76.7% without.
New method certifies generative models' robustness.
problem Certifying generative models' robustness is challenging due to non-convex sets.
method ApproxLine, a scalable certification method capturing infinite sets or distributions over them.
result ApproxLine provides sound deterministic and probabilistic guarantees.
Combining interpretability and stability methods improves DNN robustness.
problem Improving interpretability and robustness of deep neural networks.
method Combining interpretability (conductance) and stability (binary classifier) methods to detect and discard wrong predictions.
result Combining interpretability and stability methods increases model robustness.
Adversarial robustness improved by sparsity in network weights.
problem How sparsity affects adversarial robustness in neural networks.
method Theoretical proof and experimental validation of adversarial pruning methods.
result Weights sparsity improves adversarial robustness, especially through inheritance from smaller networks.
The paper improves NLI models' robustness by adding external knowledge to the attention mechanism.
problem NLI models' performance drops significantly on simple adversarial examples.
method Proposes a method to enhance NLI models' robustness by incorporating external knowledge into the attention mechanism.
result The method significantly improves the robustness of NLI models, achieving human-level performance on adversarial data.
Proposes a framework to assess model robustness to dataset shifts.
problem Evaluating model robustness to changes in setting or population.
method Derives a debiased estimator for analyzing performance on worst-case distributions.
result Demonstrates the estimator can account for realistic shifts in complex distributions.
CNNs show sensitivity to low-frequency signals due to image frequency distribution.
problem Understanding why CNNs are sensitive to low-frequency signals.
method Theoretical analysis of CNN representations in frequency space.
result CNNs sensitivity to low-frequency signals is due to the frequency distribution of natural images.
Adaptive networks improve model robustness through conditional normalization.
problem Limited robustness of adversarial-trained networks due to network capacity and training samples.
method Proposes a conditional normalization module to adapt networks during adversarial training.
result Adaptive networks outperform both clean validation accuracy and robustness compared to non-adaptive counterparts.
Data augmentation improves model robustness by enforcing a margin.
problem Understanding how data augmentation provably improves model robustness.
method Analyzed linear and nonlinear models, quantifying the margin introduced by data augmentation.
result Commonly used data augmentation techniques may only introduce significant margin after adding exponentially many points.
Mixup improves model robustness and generalization by convexly combining examples.
problem Improving model robustness and generalization.
method Using Mixup augmentation in training, which involves convex combinations of pairs of examples and their labels.
result Mixup training helps models exhibit robustness to adversarial attacks and reduces overfitting.
The paper develops a DRO framework for models robust to distributional shifts.
problem Learning models that perform well under distributional shifts.
method Distributionally robust stochastic optimization (DRO) framework.
result The DRO approach often improves performance on real tasks.
Advances AT with HE to improve model robustness.
problem Improving robustness of adversarially trained models.
method Regularizes features onto compact manifolds using hypersphere embedding.
result Integrating HE consistently enhances model robustness across various AT frameworks.
A minimalist approach generates synthetic tabular data with sparse PCA and XGBoost.
problem Generating robust synthetic tabular data for model testing.
method Minimalistic unsupervised SparsePCA encoder with XGBoost decoder.
result The method provides an alternative to raw and quantile perturbation for model robustness testing.
Adversarial training can lead to unfair accuracy disparities between different groups.
problem Adversarial training algorithms introduce unfair accuracy disparities between different groups of data.
method Propose a Fair-Robust-Learning (FRL) framework to mitigate unfairness in adversarial defenses.
result Empirical and theoretical validation of FRL's effectiveness in mitigating unfairness.
This work evaluates machine learning-based hotspot detectors on synthesized layout patterns.
problem Evaluating model robustness and generality of machine learning-based hotspot detectors.
method Developed an automatic layout generation tool to synthesize various layout patterns and tested machine learning-based detectors on these synthesized layouts.
result Machine learning-based detectors need continuous study for robustness and generality in DFM flows.
We propose a novel adversarial training method in feature space that improves model robustness and computational efficiency.
problem Improving model robustness against adversarial input perturbations with computational efficiency.
method Shift from input to feature-space perturbations, reformulating the adversarial training problem in reproducing kernel Hilbert spaces, enabling exact solution of inner maximization and efficient optimization.
result The feature-perturbed formulation is a relaxation of the original problem and provides a regularized estimator that adapts to noise and function smoothness.
Proposes robust model through Wasserstein geodesic interpolation of training data.
problem Improving model robustness through data augmentation.
method Augment data by finding worst-case Wasserstein barycenter on geodesic path.
result Improves robustness on CIFAR-10 up to 7.7% and on CIFAR-100 up to 16.8%.
Study shows removing outliers from training sets improves model robustness.
problem Vulnerability of deep neural networks to adversarial examples.
method Proposed a framework to detect and remove outliers from the training set to improve model robustness.
result Demonstrated that removing outliers from the training set can enhance model robustness.
New framework evaluates model robustness against diverse, unforeseen attacks.
problem Real-world adversarial robustness is harder to assess than research suggests.
method ImageNet-UA framework for evaluating robustness against diverse, unseen attacks.
result Standard robustness measures fail to capture unforeseen robustness.
ADT improves model robustness by learning adversarial distributions.
problem Ineffective robustness against unseen attacks due to specific attack algorithms.
method Formulates adversarial distributional training as a minimax optimization problem, learning adversarial distributions and training robust models.
result Empirical validation of ADT's effectiveness compared to state-of-the-art methods.
Meta-trained optimizers improve model robustness to image corruptions.
problem Robustness of deep learning models to input noise.
method Meta-training a learned optimizer to produce robust models.
result Meta-trained optimizers improve model robustness to Gaussian noise.
New method improves adversarial robustness without extra training steps.
problem Improving robustness of deep learning models against adversarial attacks.
method Guided Complement Entropy (GCE) training paradigm.
result GCE achieves better adversarial robustness with improved performance.
Adversarial training effectiveness varies widely due to inconsistent training settings.
problem Variability in adversarial training effectiveness due to inconsistent training settings.
method Comprehensive evaluation of 10+ adversarial training methods and their hyperparameters.
result Basic training settings like weight decay can significantly impact adversarial robustness.
New model evaluates how well models handle input faults.
problem Fault tolerance of models to input variations.
method Evaluates fault tolerance using information-based characteristic for arbitrary valid inputs.
result Proposes a new way to measure model robustness.
Paper proposes ATN to attack time series classification models.
problem Adversarial attacks on time series classification models.
method Adversarial transformation network (ATN) on a distilled model.
result Time series classification models are susceptible to adversarial attacks.
Framework uses human annotations to make models robust to spurious correlations.
problem Machine learning models fail when unmeasured variables change test distributions.
method Human annotations to augment training examples, UV-DRO objective for robustness.
result Improvements of 5-10% on digit recognition task and 1.5-5% on NYPD Police Stops analysis.
Identifies minimal training subset to flip a prediction.
problem Flipping predictions in machine learning models.
method Extended influence function for relabeling minimal subset.
result Relabeling fewer than 2% of training points can flip a prediction.
Adaptive financial dataflow system improves model robustness in dynamic markets.
problem Static historical data leads to poor performance in dynamic financial markets.
method Drift-aware dataflow system with adaptive control and optimization.
result Enhanced model robustness and improved risk-adjusted returns.