Voting ensemble of robust models improves robustness.
problem Improving robustness of defensive models against adversarial attacks.
method Hard-label voting ensemble of pretrained robust models.
result Voting ensemble can boost robust error over individual models.
VeriGB verifies robustness of gradient boosted models.
problem Proving robustness of gradient boosted models.
method VeriGB encodes model and robustness as SMT formula for verification.
result VeriGB proves robustness of large gradient boosted models.
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.
Robust Bayesian models are appealing alternatives to standard models, providing protection from data that contains outliers or other departures from the model assumptions. Historically, robust models were mostly developed on a case-by-case basis; examples include robust linear regression, robust mixture models, and bur…
This work proposes robustness curves to analyze model robustness.
problem Uncertainty in automated systems predictions due to adversarial examples.
method Introduces robustness curves to separate robustness analysis from threshold and norm choice.
result Robustness curves can qualitatively depend on the chosen norm.
Paper proposes robust generative models using VAEs.
problem Lack of robustness in generative models.
method Formally defined robust lower bound, optimized during training.
result Generative models become more robust to adversarial attacks.
SEMs fail to provide robust explanations to adversarial inputs.
problem Lack of robustness in interpretability of self-explaining models.
method Evaluation of current SEMs and creation of adversarial inputs.
result Adversarial inputs can cause significant changes in explanations without affecting model outputs.
Adversarially robust transfer learning improves model robustness with minimal data.
problem Data scarcity and computational limitations in adversarially robust transfer learning.
method Train classifiers on top of robust feature extractors from source models, or fine-tune end-to-end in target domain using lifelong learning strategies.
result Accurate and robust models can be produced with little data and without adversarial training.
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.
RobBoost optimizes a deep model ensemble for certified robustness.
problem Improving the robustness of deep models.
method Optimizes a neural network's robustness certificate through model selection and weighting.
result RobBoost forms a more robust ensemble with better certified robustness and clean accuracy.
This work introduces new ways to compare adversarial robustness of classifiers globally.
problem The limitations of point-wise measures in comparing adversarial robustness.
method Robustness curves and scale analysis to uncover global properties of robustness.
result Point-wise measures fail to capture important global properties of adversarial robustness.
Proposes a new method for nonlinear models with robustness guarantees.
problem Distributional robustness in nonlinear models with causality.
method Representation learning and identifiable representation learning.
result First causality-inspired robustness method with finite-radius guarantees in nonlinear settings.
Paper proposes robust methods for learning temporally abstract actions in reinforcement learning.
problem Learning robust reinforcement learning policies in uncertain environments.
method Robust Options Policy Iteration (ROPI) and Robust Options Deep Q Network (RO-DQN) for learning robust options.
result ROPI and RO-DQN algorithms demonstrate robustness in solving multiple tasks and generalizing over a broader range of dynamics.
Study enhances robustness of In-CVaR based regression models under perturbation and contamination.
problem Enhancing robustness of nonlinear regression models under perturbation and contamination.
method Introduces interval conditional value-at-risk (In-CVaR) and rigorously analyzes its robustness properties under both perturbation and contamination.
result The In-CVaR based estimator is qualitatively robust in terms of the Prokhorov metric if and only if the largest portion of losses is trimmed.
New GAN models robust against noisy attacks.
problem Robustness of GANs against adversarial interference.
method Introduced a perturbed discriminator to enhance robustness, explored model and training properties, and tested regularization effects.
result Variations of GANs are more robust to noisy attacks and require less regularization.
Lipschitz networks bound distributional robustness for deep neural networks.
problem Improving robustness of deep neural networks to adversarial perturbations.
method Bounding distributional robust risk with Lipschitz constant of the model.
result Distributional robustness upperbounds adversarial training risk.
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%.
Paper reviews robustness in machine learning models and discusses training and certification methods.
problem Ensuring reliability of machine learning models in safety-critical systems.
method Reviews formalisms and discusses training and certification techniques.
result Identifies future research directions in robust machine learning.
New method makes neural networks robust to various adversarial attacks.
problem Neural networks are vulnerable to specific adversarial attacks.
method Proposed MMR-Universal regularization scheme for ReLU networks.
result First provably robust models against any lp-norm for p≥1. Proposes RFQI for robust RL using offline data.
problem Learning robust policies in the presence of model uncertainty.
method RFQI algorithm using offline data to learn optimal robust policy.
result RFQI learns near-optimal robust policy under standard assumptions.
Study reinforcement learning with model misspecification, extending robust MDPs.
problem Reinforcement learning under model misspecification.
method Extending robust MDPs to model-free RL, defining robust Q-learning, SARSA, and TD-learning, proving convergence.
result Convergence to approximately optimal robust policy and value function.
Exact generalization guarantees for robust models using Wasserstein distance are established.
problem Capturing data uncertainty and distribution shifts in machine learning models.
method Establishes exact generalization guarantees for robust models based on the Wasserstein distance, covering various cases and transport costs.
result Exact generalization guarantees are provided for a wide range of cases, including deep learning objectives with nonsmooth activations.
New algorithm learns robust policies without being overly conservative.
problem Learning robust policies can be overly conservative.
method Soft-Robust Actor-Critic (SR-AC) algorithm that considers a distribution over uncertainty sets.
result SR-AC avoids the conservativeness of robust strategies while maintaining robustness.
RobustBench aims to standardize adversarial robustness evaluation in image classification.
problem Lack of systematic understanding and error-prone robustness evaluations.
method Standardized benchmark with restricted models and adaptive attacks.
result Reflects current state of the art in adversarial robustness.
This paper explores adversarial robustness of flow-based generative models.
problem Robustness of flow-based generative models to adversarial attacks.
method Theoretical and empirical analysis of adversarial robustness for simple and complex flow-based models.
result Flow-based generative models are highly sensitive to adversarial attacks, but robustness can be significantly improved using hybrid adversarial training.
This project improves model robustness to affine transformations.
problem Vulnerability of models to affine transformations.
method Evolution strategies for finding worst affine transforms.
result Effective robust models against non-parametric adversarial perturbations.
Study on robustness in linear regression models, focusing on adversarial perturbations.
problem Understanding and improving robustness in linear regression models to adversarial perturbations.
method Developed a two-stage adversarial learning framework that incorporates model structure information.
result Proved the consistency and developed the Bahadur representation of the adversarially robust estimator.
New findings suggest both robust and accurate models are possible.
problem Clarifying the relationship between adversarial robustness and generalization.
method Assumed a low-dimensional data manifold and analyzed adversarial examples.
result On-manifold adversarial examples are generalization errors, and on-manifold adversarial training boosts generalization.
Framework for robust RL in continuous control with model misspecification.
problem Model misspecification in reinforcement learning for continuous control.
method Integrates robustness into MPO algorithm through worst-case expected return objective and entropy regularization.
result Robust and soft-robust policies outperform non-robust policies in various domains.
DVERGE diversifies adversarial vulnerabilities to enhance robust ensemble models.
problem Diverse adversarial vulnerabilities for robust ensemble models.
method Isolates and diversifies adversarial vulnerabilities through distillation and training.
result Achieves higher robustness against transfer attacks compared to previous methods.
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.
Paper defends models from backdoor attacks using randomized smoothing.
problem Vulnerability of deep neural networks to backdoor attacks.
method Unified framework via randomized smoothing for both evasion and backdoor attacks; RAB robust training process.
result First provable robustness bound for backdoor attacks.
This work improves certifiably robust models by distilling knowledge from adversarially robust teachers.
problem Certifiably robust models suffer from poor standard performance.
method Knowledge distillation from adversarially robust teachers to improve standard performance.
result Distillation from adversarially robust teachers consistently improves certified training performance.
LVQ models robustness evaluated against adversarial attacks.
problem Robustness of LVQ models against adversarial attacks.
method Evaluation of three LVQ models: Generalized LVQ, Generalized Matrix LVQ, and Generalized Tangent LVQ.
result Generalized LVQ and Generalized Tangent LVQ are robust, while Generalized Matrix LVQ is not.
Proposes robust features for adversarial attacks.
problem Learning robust models to adversarial perturbations is hard.
method Develops robust features by leveraging spectral properties of dataset geometry.
result Establishes strong connections between robust features and spectral geometry.
Model improves adversarial robustness and standard accuracy with feature prioritization and regularization.
problem Inherent trade-off between adversarial robustness and standard accuracy in machine learning models.
method Feature prioritization through a nonlinear attention module and L2 feature regularization. result Improves adversarial robustness and standard accuracy compared to adversarial training.
This work proposes robust reinforcement learning methods using both offline and online data.
problem Designing robust policies against parameter uncertainties in high-dimensional systems.
method Proposes RPQ for model-free learning with historical data and HyTQ for hybrid learning with both historical and online data.
result Unified analysis and theoretical guarantees for robust optimal policies in high-dimensional systems.
Robust models may sacrifice standard accuracy for adversarial robustness.
problem Adversarial robustness vs. standard accuracy trade-off.
method Demonstrated through a simple setting, showing the inherent tension between robustness and standard accuracy.
result The trade-off between standard accuracy and adversarial robustness is a consequence of learning fundamentally different feature representations.
A robust aggregation method improves federated learning's accuracy in corrupted settings.
problem Making federated learning robust to corrupted updates from devices.
method Robust aggregation oracle based on geometric median for constant iterations of non-robust averaging.
result The robust aggregation oracle outperforms classical methods in high corruption levels.
New scalable methods for robust model learning from large datasets.
problem Training robust models resistant to data distribution shifts.
method Composite optimization for distributionally robust optimization (DRO).
result Scalable methods for learning robust models from large datasets.
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.
Adversarially robust models transfer better than standard models in image classification.
problem Improving transfer learning performance in image classification.
method Focused on adversarially robust ImageNet classifiers, compared to standard models.
result Adversarially robust models yield improved accuracy on downstream classification tasks.
New Stein operator improves robustness in model inference.
problem Improving robustness in inference for unnormalized models.
method Density-power weighted Stein operator (γ-Stein operator). result Robust methods for goodness-of-fit testing and posterior approximation.
Discussing issues in robust clustering, especially with Gaussian models.
problem Handling outliers and ambiguity in clustering groups.
method Focus on Gaussian mixture model, examining formal definitions, interactions, and tuning decisions.
result Outliers can confuse clustering groups and existing stability measures fail with them.
This paper explores the trade-off between spatial and adversarial robustness in neural networks.
problem Understanding the trade-off between spatial and adversarial robustness in neural networks.
method Quantitative analysis and empirical testing with curriculum learning.
result Spatial robustness and adversarial robustness are quantitatively related and can be improved simultaneously.
Simpler classifiers are more robust to adversarial perturbations.
problem Vulnerability of deep neural networks to small adversarial perturbations.
method Investigating the connection between simplicity and robustness in classifiers.
result Simpler classifiers (fewer output classes) are less susceptible to adversarial perturbations.
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.
SCORE resolves the robustness vs accuracy trade-off by redefining robust error.
problem The inherent trade-off between robustness and accuracy in adversarial training.
method SCORE defines local equivariance as the ideal robust behavior, leading to a new robust error metric.
result SCORE reconciles robustness and accuracy, improving model performance on RobustBench.