This paper provides a comprehensive benchmark and taxonomy for certifiably robust DNN defenses.
problem Certifiably robust defenses against adversarial attacks for deep neural networks.
method Taxonomy and benchmark of certifiably robust approaches.
result First comprehensive benchmark of certifiably robust approaches on different datasets.
Efficiently certifies global robustness of large neural networks with probabilistic guarantees.
problem Certifying robustness of large neural networks in a scalable and efficient manner.
method Sampling an ε-net and invoking a local robustness oracle.
result Certifies a probabilistic relaxation of robustness efficiently and globally.
Develops robust methods for computer vision representation learning.
problem Noise and outliers frustrate unsupervised learning of latent representations.
method New robust PCA and spectral clustering methods.
result Superior performance on real-world test sets.
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.
Robust boosting improves regression accuracy in noisy data.
problem Handling outliers in non-parametric regression.
method Two-stage approach: robust residual scale minimization followed by bounded loss optimization.
result Robust boosting outperforms standard methods in outlier-prone data.
In support vector machine (SVM) applications with unreliable data that contains a portion of outliers, non-robustness of SVMs often causes considerable performance deterioration. Although many approaches for improving the robustness of SVMs have been studied, two major challenges remain in robust SVM learning. First, r…
New approach for prudent risk evaluation using model aggregation.
problem Risk evaluation and optimization under uncertainty.
method Model Aggregation (MA) approach based on stochastic dominance.
result Produces robust risk evaluation and distributional models.
Enhances deep learning models to resist adversarial attacks.
problem Protecting deep learning models from adversarial examples.
method Combines two mechanisms: increased robustness at the cost of accuracy and improved accuracy without robustness guarantee.
result Combining mechanisms provides robustness against adversarial examples while maintaining accuracy.
New method makes CNN interpretations robust to adversarial attacks.
problem Adversarial attacks on CNN interpretation maps.
method Renyi Differential Privacy (RDP) for robust interpretation.
result Certifiable top-k robustness and improved experimental robustness. NoL approach improves adversarial robustness by modeling random noise during training.
problem Improving neural network robustness against adversarial attacks.
method Implicit generative modeling of random noise during training.
result Models trained with NoL perform better against a wide range of adversarial attacks.
ORL tackles robust online learning from noisy data.
problem Learning from noisy data with outliers in large-scale settings.
method ORL approach for online robust learning, scalable and robust.
result Provable robustness and efficiency advantages demonstrated.
Paper presents a robust Kalman filter for state estimation.
problem Robust state estimation under process and measurement noise.
method Generalized Bayesian approach to a Weighted Observation Likelihood Filter (WoLF) framework.
result Achieved robust state estimation against both process and measurement noise.
Develops a two-stage approach for robust tensor completion of visual data.
problem Estimating missing values in high-order data with outliers.
method Coarse-to-fine framework and M-estimator-based robust tensor ring recovery.
result Superior performance compared to state-of-the-art robust algorithms.
This paper examines how optimization methods affect the reliability of detecting inputs outside a model's training distribution.
problem The unreliability of deep neural networks on out-of-distribution inputs.
method Analysis of optimization methods' impact on OOD detection approaches.
result Optimization methods significantly influence the robustness of OOD detection approaches.
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…
Proposes a robust risk measure to minimize capital errors.
problem Minimizing capital determination errors due to risk overestimation and underestimation.
method Uses supremum over probability measures to minimize overestimation and underestimation costs.
result Guarantees the existence of a solution and explores properties of minimizer and minimum as risk and deviation measures.
Bayesian approach improves learning in RMDPs with faster adaptation.
problem Learning robust policies in RMDPs with changing or adversarial dynamics.
method Introduce Uncertainty Robust Bellman Equation (URBE) and DQN-URBE algorithm.
result URBE-based strategy leads to better trade-off between robustness and exploration.
This paper improves offline contextual bandits using distributional robustness.
problem Improving offline contextual bandits with robustness.
method Extends Distributionally Robust Optimization (DRO) for offline contextual bandits, introducing a convex reformulation of Counterfactual Risk Minimization.
result Automatic calibration of asymptotic confidence intervals for policy optimization.
Enhances survival analysis predictions with a robust learning approach.
problem Improving robustness and accuracy in survival analysis predictions.
method Integrates Distributionally Robust Learning (DRL) into Cox regression using Wasserstein distance-based ambiguity set.
result Demonstrates superior performance in prediction accuracy and robustness compared to traditional methods.
REBEC improves robustness of wind wave models using evolutionary techniques.
problem Improving the calibration of numerical wind wave models to local conditions.
method Robust evolutionary-based calibration approach (REBEC) for building stochastic ensemble of models.
result REBEC outperforms baseline SPEA2 in achieving a balance between model quality and robustness.
This paper proposes BAT to balance accuracy and robustness in adversarial training.
problem Balancing accuracy and robustness in adversarial training models.
method Blind adversarial training (BAT) uses a cutoff-scale strategy to adaptively estimate a nonuniform budget for AEs.
result BAT improves the overall robustness of adversarial training models.
Empirical study finds robust optimization can improve portfolio performance in Indian markets.
problem Comparing robust optimization to Markowitz model for portfolio performance.
method Three robust optimization models (box, ellipsoidal, separable uncertainty sets) tested on Indian market data.
result Robust optimization can be a viable alternative to Markowitz model in real market setups.
New probabilistic approach to neural network robustness.
problem Challenges in verifying neural network robustness.
method Probabilistic robustness approach, abstract interpretation, importance sampling.
result Practical algorithm for checking probabilistic robustness of neural networks.
We consider large-scale Markov decision processes (MDPs) with parameter uncertainty, under the robust MDP paradigm. Previous studies showed that robust MDPs, based on a minimax approach to handle uncertainty, can be solved using dynamic programming for small to medium sized problems. However, due to the "curse of dimen…
SOAR improves deep networks' robustness against adversarial examples.
problem Improving deep neural networks' robustness against adversarial examples.
method Formulated adversarial robustness problem under robust optimization framework, approximated loss function using second-order Taylor series expansion.
result SOAR significantly improves robustness of networks against adversarial perturbations.
New approach to robust Gaussian process regression with bias model.
problem Outliers in Gaussian process regression.
method Models outliers as biased observations and uses bias terms in likelihood.
result Robust and accurate GP estimates for various outlier scenarios.
New approach improves model generalization through distributionally robust learning.
problem Improving model generalization in machine learning.
method Stochastic gradient descent applied to the outer minimization problem, with gradient estimation through multi-level Monte Carlo randomization.
result Our approach yields significant benefits over previous work in numerical experiments.
New algorithm ATENT improves adversarial robustness in neural networks.
problem Improving neural network robustness against adversarial attacks.
method Proposes a new loss function with entropic regularization for training robust neural networks.
result ATENT achieves competitive robust classification accuracy on benchmark datasets.
New framework tightens certified robustness gaps in machine learning models.
problem Persistent gap between theoretical certified robustness and empirical accuracy.
method Leverages Lipschitz continuity and novel confidence intervals.
result Improves robust accuracy, compressing the gap between theory and practice.
Considering mean-variance portfolio problems with uncertain model parameters, we contrast the classical absolute robust optimization approach with the relative robust approach based on a maximum regret function. Although the latter problems are NP-hard in general, we show that tractable inner and outer approximations e…
This paper improves machine learning models' robustness against evasion attacks using randomness.
problem Evasion attacks that adapt to machine learning models to avoid detection.
method Incorporates randomness into both training and application phases of machine learning models.
result The proposed randomization-based approach further improves the robustness of machine learning models, especially random forest.
Paper proposes robust and sparse GLM regression using stochastic optimization.
problem Sparse GLM's lack robustness against outliers in high-dimensional data.
method Robust and sparse linear regression based on γ-divergence with stochastic optimization. result The proposed method outperforms existing methods in numerical experiments and real data analysis.
New method improves robust sparse association estimation.
problem Outliers in high-dimensional data.
method Splitting robust estimation into optimization phases, using augmented Lagrangian and adaptive gradient descent.
result Improved precision over existing methods.
New method assesses neural network robustness with statistical estimates.
problem Assessing neural network robustness under input models.
method Statistical approach based on estimating the proportion of inputs violating a property.
result Provides an informative notion of network robustness, scaling to larger networks.
Two approaches integrate qualitative views into portfolio optimization, showing aggregation methods outperform robust optimization.
problem Incorporating qualitative views into portfolio optimization models.
method Robust optimization and order aggregation methods.
result Aggregation methods outperform robust optimization in portfolio performance analysis.
FedGVI improves FL robustness to model misspecification.
problem Limited robustness in FL approaches to model misspecification.
method Probabilistic Federated Learning framework that generalizes previous methods.
result FedGVI provides robust and calibrated predictions under model misspecification.
A robust method for off-policy evaluation in contextual bandits.
problem Evaluating policies when direct methods are unavailable.
method Robust regression approach to off-policy evaluation.
result Superior empirical performance across benchmarks.
A single robust classifier handles complex image synthesis tasks.
problem Challenging image synthesis tasks.
method Adversarial robustness training of a single classifier.
result Direct manipulation of salient features in input images.
Scaff-PD improves fairness and robustness in federated learning with reduced communication.
problem Improving fairness and robustness in federated learning with limited communication.
method Scaff-PD uses a family of distributionally robust objectives and an accelerated primal dual algorithm with bias-corrected steps.
result Scaff-PD achieves significant gains in communication efficiency and convergence speed while maintaining fairness and robustness.
Paper develops a robust hedging framework to reduce market risk and uncertainty.
problem Managing uncertainty and risk exposure in portfolio management.
method Combines high-frequency realized variance, covariance measures, and autoregressive models for multi-step volatility forecasting. Uses a box-uncertainty robust optimization scheme to derive a closed-form solution for the robust hedge ratio.
result Robust hedge ratios are more stable and entail lower turnover than standard dynamic hedges, improving downside protection and risk-adjusted performance.
New approach improves robustness of deep neural networks without overfitting.
problem Adversarial vulnerability of deep neural networks.
method Non-zero-sum bilevel formulation of adversarial training.
result Algorithm matches and outperforms state-of-the-art attacks, maintains robustness, and avoids overfitting.
The paper explores optimistic robust optimization for machine learning problems.
problem Addressing uncertainty in machine learning models using optimistic robust optimization.
method Develops optimistic robust optimization techniques for machine learning problems, including robust linear programming and sparsity-inducing regularization.
result Optimistic robust optimization can provide new interpretations and solutions for existing machine learning challenges.
New metrics show current interpretability methods lack robustness.
problem Lack of robustness in interpretability methods.
method Introduce metrics to quantify robustness and propose ways to enforce robustness.
result Current interpretability methods do not perform well according to introduced robustness metrics.
Enhances robustness for time series classification using self-ensemble method.
problem Limited adversarial robustness in time series classification.
method Proposes a self-ensemble method to improve Randomized Smoothing's robustness certification.
result Demonstrates superior robustness compared to baseline approaches.
Accelerates DNN robustness verification with target labels.
problem Improving the robustness of deep neural networks against adversarial attacks.
method Guiding robustness verification with target labels, reducing search space and using symbolic interval propagation and linear relaxation.
result Significantly improves DNN verification speed by 36X, especially when perturbation distance is reasonable.
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.
One epoch training yields certifiably robust models.
problem Vulnerability of machine learning models to adversarial attacks.
method Deterministic certification approach based on regularized loss.
result Certifiable robust models achieved in one epoch.
The errors-in-variables (EIV) regression model, being more realistic by accounting for measurement errors in both the dependent and the independent variables, is widely adopted in applied sciences. The traditional EIV model estimators, however, can be highly biased by outliers and other departures from the underlying a…