A new robust time series distance metric for k-NN classification.
problem Robustness against arbitrary data contamination in time series classification.
method Proposes a novel distance metric with worst-case O ( n log n ) \mathcal{O}(n\log n) O ( n log n ) complexity. result Demonstrates competitive classification accuracy in k-NN time series classification.
Quantum classification robustness improved via quantum hypothesis testing.
problem Vulnerability of quantum classification algorithms to input perturbations.
method Formalized link between quantum hypothesis testing and robustness, developed practical protocols.
result Tight robustness condition independent of noise source (natural or adversarial).
Proposes a robust method for counterfactual classification.
problem Decision-making under hypothetical scenarios.
method Doubly-robust nonparametric estimator for counterfactual classification.
result Robust against nuisance model misspecification, can attain fast n \sqrt{n} n rates. Study improves adversarial classification using distributionally robust models.
problem Improving robustness against adversarial attacks in classification models.
method Distributionally robust chance constraints with Wasserstein ambiguity, reformulated as a regularized ramp loss minimization problem.
result Standard descent methods can converge to the global minimizer for the distributionally robust adversarial classification model.
New method for robust learning from batches, even adversarial ones.
problem Learning from batches that may be corrupt or adversarial.
method General framework for robust learning, derived from optimal robust algorithms.
result First robust agnostic learning algorithms for various distributions.
The paper investigates AI robustness through experiments and statistical analysis.
problem Inaccurate AI predictions can lead to safety and adoption issues.
method Design of experiments framework to study AI classification robustness.
result AI algorithms' robustness is influenced by various factors.
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…
Previous work on adversarially robust neural networks for image classification requires large training sets and computationally expensive training procedures. On the other hand, few-shot learning methods are highly vulnerable to adversarial examples. The goal of our work is to produce networks which both perform well a…
Novel neural network approximates exact distance for robust classification.
problem Adversarial attacks on neural networks in safety-critical systems.
method Signed Distance Classifiers (SDCs) and Unitary-Gradient Neural Network.
result Approximates exact distance from classification boundary for certifiable predictions.
The paper tackles robust classification trees for distribution shifts, improving accuracy in public health and social work.
problem Learning robust classification trees for high-stakes settings with distribution shifts.
method Mixed-integer robust optimization technology to reformulate as a two-stage linear robust optimization problem.
result Increase of up to 12.48% in worst-case accuracy and 4.85% in average-case accuracy.
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.
Adversarial robustness improved by abstaining from decisions.
problem Improving classification accuracy in the presence of adversarial perturbations.
method Introducing an abstain option in binary classification problems, using metrics to quantify performance and robustness.
result There is a tradeoff between nominal performance and adversarial robustness.
The paper sets lower bounds for adversarial robustness in multiclass classification.
problem Adversarial robustness in multiclass classification with arbitrary loss functions.
method Dual and barycentric reformulations for robust risk minimization.
result Sharp lower bounds for adversarial risks are computed efficiently.
Unified smoothing for robust classification improves accuracy.
problem Improving robustness of classifiers against adversarial attacks.
method Learned smoothed densities and randomized smoothing.
result Provable robust accuracies higher than state-of-the-art defenses.
Paper tackles robust imitation learning from noisy demonstrations.
problem Learning from noisy demonstrations is challenging.
method Optimizes a classification risk with a symmetric loss, combining pseudo-labeling and co-training.
result Our method is more robust than state-of-the-art methods.
The paper explores robust classifiers for imbalanced Gaussian data.
problem Adversarial robustness in machine learning with imbalanced data.
method Developed exact and approximate Bayes-optimal robust classifiers for Gaussian classification problems.
result Revealed fundamental tradeoffs between standard and robust accuracy.
Adversarial training improves robustness of halfspaces in noisy data.
problem Learning robust halfspaces in the presence of label noise.
method Adversarial training with binary cross-entropy or nonconvex sigmoidal loss.
result Adversarial training yields robust halfspaces with improved classification error.
New algorithm uses random projections for robust, sparse data classification.
problem Improving robustness and sparsity in data classification.
method Randomly projects data into a high-dimensional space, truncates small entries, and applies a cap operation.
result The method enhances classification accuracy with minimal loss, especially in noisy conditions.
Current techniques in machine learning are so far are unable to learn classifiers that are robust to adversarial perturbations. However, they are able to learn non-robust classifiers with very high accuracy, even in the presence of random perturbations. Towards explaining this gap, we highlight the hypothesis that $\te…
This text is about geometric structures imposed by robust dynamical behaviour. We explain recent results towards the classification of partially hyperbolic systems in dimension 3 using the theory of foliations and its interaction with topology. We also present recent examples which introduce a challenge in the classifi…
Improves deep learning robustness by considering task and model.
problem Adversarial attacks on deep learning systems.
method Binary and interval label encoding strategy to redefine classification tasks and design corresponding loss functions.
result Our method enhances robustness without sacrificing accuracy.
We continue the study of statistical/computational tradeoffs in learning robust classifiers, following the recent work of Bubeck, Lee, Price and Razenshteyn who showed examples of classification tasks where (a) an efficient robust classifier exists, in the small-perturbation regime; (b) a non-robust classifier can be l…
Hierarchical randomized smoothing improves model robustness for complex data.
problem Certifying robustness on complex data (e.g. images, graphs) is challenging.
method Add random noise to a randomly selected subset of entities in a hierarchical manner.
result Hierarchical randomized smoothing yields stronger robustness guarantees with high accuracy.
Proposes a robust 3D classification method for sparse point clouds.
problem Invariance to rotation, positional shift, scaling, and robustness to point sparsity in point cloud classification.
method Introduces a graph-based feature learning approach with an end-to-end neural network.
result Significantly improves 3D object classification and retrieval tasks with sparse point clouds.
Paper develops a robust classifier for Gaussian mixture models under sparse adversarial perturbations.
problem Classifying data under sparse adversarial perturbations for Gaussian mixture models.
method Develops FilTrun algorithm with filtration and truncation modules.
result Characterizes optimal robust classifier and robust classification error.
Paper provides optimal statistical guarantees for adversarial robustness in Gaussian classification.
problem Understanding statistical risks for adversarial robustness in Gaussian classification models.
method Established minimax lower bounds and designed an efficient estimator for excess risk.
result Optimal minimax guarantees for excess risk under Gaussian mixture model with AdvSNR.
Score-based generative models achieve state-of-the-art classification accuracy on CIFAR-10.
problem Improving classification accuracy on natural image datasets.
method Score-based generative models applied to CIFAR-10.
result Score-based models achieve state-of-the-art classification accuracy on CIFAR-10.
Recently, techniques have been developed to provably guarantee the robustness of a classifier to adversarial perturbations of bounded L_1 and L_2 magnitudes by using randomized smoothing: the robust classification is a consensus of base classifications on randomly noised samples where the noise is additive. In this pap…
Study analyzes and enhances robustness of neural networks for classification and regression.
problem Understanding and improving robustness of neural network predictions.
method Computes reachable sets of neural networks using over- and under-approximations.
result Approach outperforms adversarial attacks and state-of-the-art classifier verification methods.
Evaluates deep learning models in histopathology for robustness and classification strategies.
problem Lack of comprehensive evaluation of histopathology models beyond accuracy.
method Developed a new methodology to evaluate models on five histopathology datasets, including vision transformers and CNNs.
result Identified insights into cancer classification strategies and robustness against stain variations.
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.
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.
Study proves existence of robust classifiers in multiclass adversarial training.
problem Proves existence of robust classifiers in multiclass adversarial training.
method Three models of adversarial training in multiclass classification, proving existence of Borel measurable robust classifiers.
result Proves existence of Borel measurable robust classifiers in each model.
AdaBoost improves binary classification in robust one-bit compressed sensing with adversarial errors.
problem Binary classification in robust one-bit compressed sensing with adversarial errors.
method AdaBoost and max- ℓ 1 \ell_1 ℓ 1 -margin-classifier approach, with convergence rates improved under certain feature conditions. result Improved convergence rates and explanation for harmless interpolating adversarial noise.
Bayesian classifier improves robustness with optimistic score ratio.
problem Limited information on class-conditional distribution.
method Optimistic score ratio for robust binary classification.
result Bayesian classifier using optimistic score ratio is robust and computationally tractable.
Study shows current image classification models lack robustness to real-world dataset shifts.
problem Robustness of current image classification models to natural distribution shifts in real datasets.
method Evaluation of 204 ImageNet models in 213 different test conditions.
result Little to no transfer of robustness from synthetic to natural distribution shifts.
Mapper-GIN simplifies 3D point cloud classification with lightweight structure.
problem Robust 3D point cloud classification under corruption.
method Mapper algorithm for structural decomposition, GIN for graph classification.
result Mapper-GIN achieves competitive accuracy with minimal parameters.
Logitboost is an influential boosting algorithm for classification. In this paper, we develop robust logitboost to provide an explicit formulation of tree-split criterion for building weak learners (regression trees) for logitboost. This formulation leads to a numerically stable implementation of logitboost. We then pr…
Many leading classification algorithms output a classifier that is a weighted average of kernel evaluations. Optimizing these weights is a nontrivial problem that still attracts much research effort. Furthermore, explaining these methods to the uninitiated is a difficult task. Letting all the weights be equal leads to …
Paper proposes S 2 S^2 S 2 ConvSCN for robust subspace clustering and classification.
problem Insufficient handling of nonlinear manifolds, data corruptions, and out-of-sample data.
method Self-supervised convolutional subspace clustering network ( S 2 S^2 S 2 ConvSCN) with FC layer, CIM for robustness, and BD regularization. result Robust S 2 S^2 S 2 ConvSCN outperforms baseline on unseen data. We tackle imbalanced classification by weighting losses and derive robust risks.
problem Imbalanced classification where a label has low marginal probability.
method We examine convergence rates of weighted risks, define robust risks, and derive new robust risk problems.
result We show that particular weightings lead to conditional value at risk (CVaR) and derive new robust risk problems.
Unified framework improves neural network robustness against label noise and adversarial attacks.
problem High sensitivity of neural networks to data contamination, including label noises and adversarial perturbations.
method Unified minimum-divergence estimation problem, rSDNet framework.
result Improves robustness to label corruption and adversarial attacks while maintaining competitive accuracy on clean data.
Proposes a method to improve classification robustness against label noise.
problem Improving classification robustness against label noise.
method Extends a simple regression approach to classification, modeling labels as samples from a logistic-normal distribution.
result The method improves robustness against label noise in classification.
New method improves neural network interpretability against adversarial attacks.
problem Adversarial attacks can hide from neural network interpretability methods.
method Develops an interpretability-aware defensive scheme promoting robust interpretation.
result Achieves both robust classification and robust interpretation.
Paper tackles leveraging unlabeled data for PU classification and robust generation.
problem Scarcity of labeled data in machine learning problems.
method Introduces a novel training framework that simultaneously targets PU classification and conditional generation using extra unlabeled data.
result Proves the effectiveness of a Classifier-Noise-Invariant Conditional GAN (CNI-CGAN) that enhances PU classifier performance and leverages extra data.
Paper tackles robust classification under class-dependent domain shift.
problem Class-dependent domain shift in machine learning.
method Defined a simple optimization problem with an information theoretic constraint and solved it using neural networks.
result Demonstrated that the proposed method can learn robust classifiers that generalize well to unseen domains.
In spite of achieving revolutionary successes in machine learning, deep convolutional neural networks have been recently found to be vulnerable to adversarial attacks and difficult to generalize to novel test images with reasonably large geometric transformations. Inspired by a recent neuroscience discovery revealing t…
This paper introduces a method to make deep neural networks more robust to adversarial attacks.
problem Deep neural networks are vulnerable to adversarial attacks, leading to incorrect classifications.
method Introduces sensible adversarial learning to balance robustness and natural accuracy.
result Demonstrates that the Bayes classifier is the most robust multi-class classifier under sensible adversarial learning.