Boosts barely robust learners to be more adversarially robust.
problem Learning predictors robust to small perturbations on a small fraction of data.
method Oracle-efficient algorithm for robustness with larger perturbation set.
result Qualitative and quantitative equivalence between strongly robust and barely robust learning.
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.
Neural Networks have been shown to be sensitive to common perturbations such as blur, Gaussian noise, rotations, etc. They are also vulnerable to some artificial malicious corruptions called adversarial examples. The adversarial examples study has recently become very popular and it sometimes even reduces the term "adv…
New research shows flat minima in robust loss landscapes correlate with good adversarial robustness.
problem Adversarial training leads to robust overfitting, poor robust generalization.
method Average- and worst-case metrics to measure flatness in robust loss landscapes.
result Flatness in robust loss landscapes correlates with good adversarial robustness.
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.
Study privacy and robustness in learning halfspaces, proving hard trade-offs.
problem Balancing privacy and robustness in learning halfspaces.
method Proves nearly tight bounds on sample complexity for robust private learning of halfspaces.
result Robust and private learning is harder than robust or private learning alone.
We introduce a new metric to evaluate corruption robustness of ML classifiers.
problem Evaluating corruption robustness of machine learning classifiers.
method We propose a test data augmentation method using minimal class separation distance to derive a robustness distance ε and a metric MSCR.
result The MSCR metric allows interpretable comparison of classifier robustness on different datasets.
Robust learning method combines kernel smoothing and robust optimization.
problem Certifying robustness against distribution shifts in machine learning models.
method Adapting integral operator using supremal convolution for robustness, leveraging optimal transport.
result The method provides theoretical guarantees for certified robustness and competitive performance.
Study shows how bias in optimization affects robustness in adversarial settings.
problem Understanding and mitigating implicit bias in adversarially robust models.
method Analyzes the implicit bias in robust empirical risk minimization and its impact on generalization.
result Implicit bias in optimization can significantly affect robust generalization.
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.
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.
Develops robust learning framework under distributional perturbations.
problem Learning robust to data distributional changes.
method Distributionally Robust Optimization (DRO) under Wasserstein metric.
result Establishes performance guarantees and tractable formulations.
The study examines robust decision-making in volatile financial markets, finding action robustness is more impactful than uncertainty tolerance.
problem Sequential decision making in high-frequency markets under evolving uncertainty.
method Analyzes two dimensions of robustness: uncertainty tolerance and action robustness, using simulations and empirical evidence.
result Action robustness has a larger impact on profitability than uncertainty tolerance, and excessive robustness can reduce profitability in illiquid markets.
Making neural networks robust against adversarial inputs has resulted in an arms race between new defenses and attacks. The most promising defenses, adversarially robust training and verifiably robust training, have limitations that restrict their practical applications. The adversarially robust training only makes the…
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.
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.
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 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.
Paper proposes a robust metric learning algorithm.
problem Robustness of metric learning against adversarial perturbations is insufficient.
method Proposes a novel Mahalanobis distance metric learning algorithm.
result Certifiable robustness improvement over Euclidean distance.
Study improves image classifier robustness to random p-norm corruptions.
problem Improving robustness of image classifiers to real-world imperceptible corruptions.
method Training and testing with random p-norm corruptions, evaluating robustness against different p-norms.
result Training with a combination of p-norm corruptions significantly improves robustness.
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.
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 mechanisms from primate vision improve neural network robustness.
problem Demonstrating robust neural networks to small adversarial perturbations.
method Investigated two biologically plausible mechanisms: non-uniform retina sampling and receptive field diversity.
result Non-uniform retina sampling and receptive field diversity improve adversarial robustness.
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%.
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.
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.
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.
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.
RATIO improves neural network robustness and explainability.
problem Neural networks' lack of robustness to adversarial changes and uncertainty on out-distribution samples.
method RATIO: Adversarial Training on In- and Out-distribution.
result RATIO leads to robust models with reliable confidence estimates on out-distribution samples.
Paper explores robust regression methods and their bias-variance trade-off.
problem Understanding the trade-off between robust estimation and optimization methods.
method Examines traditional outlier-resistant robust estimation and robust optimization.
result Both methods follow converse strategies due to a bias-variance trade-off.
Proposes a framework for defining robustness in neural networks.
problem Lack of a precise foundation for robustness concepts in neural networks.
method Develops a rigorous and flexible framework based on mathematical postulates.
result Proposes new learning approaches for optimizing robustness objectives.
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. 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…
This paper investigates how network width and depth affect adversarially robust DNNs.
problem Understanding architectural configurations for adversarially robust DNNs.
method Comprehensive investigation on the impact of network width and depth on adversarial robustness.
result Optimal architectural configuration for adversarial robustness exists and can improve robustness.
Robust reinforcement learning aims to produce policies that have strong guarantees even in the face of environments/transition models whose parameters have strong uncertainty. Existing work uses value-based methods and the usual primitive action setting. In this paper, we propose robust methods for learning temporally …
Robust Reinforcement Learning aims to derive optimal behavior that accounts for model uncertainty in dynamical systems. However, previous studies have shown that by considering the worst case scenario, robust policies can be overly conservative. Our soft-robust framework is an attempt to overcome this issue. In this pa…
We provide a framework for incorporating robustness -- to perturbations in the transition dynamics which we refer to as model misspecification -- into continuous control Reinforcement Learning (RL) algorithms. We specifically focus on incorporating robustness into a state-of-the-art continuous control RL algorithm call…
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.
Knowledge distillation is effective for producing small, high-performance neural networks for classification, but these small networks are vulnerable to adversarial attacks. This paper studies how adversarial robustness transfers from teacher to student during knowledge distillation. We find that a large amount of robu…
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.
New methods show robustness and accuracy can coexist.
problem Inevitability of robustness-accuracy tradeoff in deep learning.
method Prove robustness and accuracy achievable through locally Lipschitz functions; explore combining dropout with robust training methods.
result Achieving robustness and accuracy requires methods imposing local Lipschitzness and deep learning generalization techniques.
Robustness to distributional shift is one of the key challenges of contemporary machine learning. Attaining such robustness is the goal of distributionally robust optimization, which seeks a solution to an optimization problem that is worst-case robust under a specified distributional shift of an uncontrolled covariate…
Robust learning mixtures of linear regressions improve robustness.
problem Improving robustness in learning mixtures of linear regressions.
method Connecting mixtures of linear regressions and mixtures of Gaussians with thresholding for a quasi-polynomial time algorithm.
result The algorithm has significantly better robustness than previous results.
Study on proper learning under relaxed worst-case robust loss for VC classes.
problem Proper adversarially robust PAC learning under relaxed worst-case robust loss.
method Introduced a family of robust loss relaxations and showed their effectiveness for proper learnability.
result VC classes are properly PAC learnable with sample complexity close to standard PAC learning setup.
Federated learning is the centralized training of statistical models from decentralized data on mobile devices while preserving the privacy of each device. We present a robust aggregation approach to make federated learning robust to settings when a fraction of the devices may be sending corrupted updates to the server…
The paper develops robust risk measures for uncertain loss positions.
problem Risk assessment for loss positions with uncertain distributions.
method Robust optimized certainty equivalents and generalized quantiles are proposed and analyzed.
result Robust expectiles with specific penalization functions are coherent risk measures.
Improves robust transfer learning with side information.
problem Addressing environmental shift in MDPs with side information.
method Estimate-centered uncertainty sets with side information integration.
result Improved robust policy with reduced sub-optimality gap.
Paper explains adversarial training's robust overfitting through a minimax game perspective.
problem Adversarial training suffers from robust overfitting after learning rate decay.
method Viewing adversarial training as a dynamic minimax game, analyzing how LR decay breaks balance and leads to overfitting.
result ReBalanced Adversarial Training (ReBAT) alleviates robust overfitting without sacrificing robustness.