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.
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.
Study robust estimation under varying corruption probabilities in data.
problem Robust estimation in scenarios with heterogeneous corruption rates.
method Developed estimators for mean and regression under various corruption patterns.
result Optimal estimators can discard corrupted samples beyond a specific threshold.
Robust algorithm optimizes corrupted Gaussian process bandits.
problem Sequential optimization of corrupted, expensive reward functions.
method Robust GP Phased Elimination (RGP-PE) algorithm.
result Algorithm balances robustness to corruptions with exploration and exploitation.
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Unlike recent robustness research, this benchmark evaluates performan…
Study robust mean estimation under coordinate-level corruptions using Hamming distance.
problem Robust mean estimation under realistic coordinate-level corruptions.
method Introduce a novel Hamming distance-based measure and present information-theoretic analysis.
result Data cleaning-inspired approaches can match information theoretic bounds for robust mean estimation.
In this paper we establish rigorous benchmarks for image classifier robustness. Our first benchmark, ImageNet-C, standardizes and expands the corruption robustness topic, while showing which classifiers are preferable in safety-critical applications. Then we propose a new dataset called ImageNet-P which enables researc…
New method makes robust estimators work without knowing corruption levels.
problem Robust estimation algorithms struggle with unknown corruption levels.
method Abstracted geometric puzzle solution to universal meta technique.
result Converts any robust estimator to work without corruption bounds.
RILA learns HQMMs robustly against adversarial corruption.
problem Robustness of HQMM learning algorithms under adversarial perturbations.
method Adversarially Corrupted HQMM (AC-HQMM) and Robust Iterative Learning Algorithm (RILA).
result RILA outperforms existing algorithms in convergence stability, corruption resilience, and physical validity.
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.
Unified framework for corruption-robust linear bandits with optimal gap-dependent misspecification bounds.
problem Effective learning in linear bandits with corrupted rewards across different corruption models.
method Unified framework for analyzing strong and weak corruption, connection to gap-dependent misspecification, and specialized algorithm.
result Optimal bounds for gap-dependent misspecification in linear bandits.
This study tackles adversarial corruption in model-based reinforcement learning.
problem Adversarial corruption in model-based reinforcement learning.
method Maximum likelihood estimation (MLE) approach for learning transition model in both online and offline settings.
result Proves a regret of i l d e O ( T + C ) ilde{\mathcal{O}}(\sqrt{T} + C) i l d e O ( T + C ) for CR-OMLE and a suboptimality of O ( C / n ) \mathcal{O}(C/n) O ( C / n ) for CR-PMLE. Robust tests control type I error under data corruption.
problem Effective hypothesis testing under data corruption.
method General permutation tests using kernel MMD and HSIC metrics.
result Robust tests are minimax optimal and outperform private tests.
Adaptive learning method identifies and corrects corrupted data.
problem Robust learning from corrupted training sets.
method Identifies corrupted and non-corrupted samples with latent Bernoulli variables, formulates as likelihood maximization with marginalized latent variables, solved via variational inference and Expectation-Maximization.
result Improves over state-of-the-art by automatically inferring corruption level with minimal overhead.
Estimates GLMs robustly against label corruptions.
problem Learning GLMs under adversarial label corruptions.
method Iterative trimmed maximum likelihood estimator.
result Achieves minimax near-optimal risk.
New algorithm robustly learns from corrupted demonstrations, even with constant fraction of noise.
problem Learning from corrupted demonstrations where a fraction of data is noise or outliers.
method Proposes a novel robust algorithm using a Median-of-Means (MOM) objective.
result Guarantees accurate policy estimation even with constant fraction of outliers, similar to classical methods in expert demonstration settings.
Conventional sampling techniques fall short of drawing descriptive sketches of the data when the data is grossly corrupted as such corruptions break the low rank structure required for them to perform satisfactorily. In this paper, we present new sampling algorithms which can locate the informative columns in presence …
New algorithm robust to outliers in Bayesian Optimization.
problem Vulnerability of Bayesian Optimization to extreme outliers.
method Introduces a new adversary with a frequency-bounded corruption budget and derives RCGP-UCB algorithm.
result Achieves sublinear regret in the presence of up to O ( T 1 / 4 ) O(T^{1/4}) O ( T 1/4 ) and O ( T 1 / 7 ) O(T^{1/7}) O ( T 1/7 ) corruptions with possibly infinite magnitude. Study on measuring vulnerability of neural network parameters via corruption.
problem Understanding the robustness and generalization of deep neural networks.
method Proposes an indicator to measure parameter robustness via parameter corruption and provides a gradient-based estimation.
result Demonstrates the effectiveness of the proposed indicator and training method in improving parameter robustness and accuracy.
Simple noise training improves image recognition robustness.
problem Modern neural networks struggle with unseen image corruptions.
method Additive Gaussian and Speckle noise training, adversarial training against worst-case noise.
result Significant improvement in robustness on ImageNet-C and MNIST-C benchmarks.
RGI improves robustness of GAN-inversion for image restoration and anomaly detection.
problem Robustness of GAN-inversion to unknown gross corruptions.
method Proposes RGI and R-RGI methods with provable robustness guarantees.
result Restored images and corrupted region masks converge to ground truth under mild assumptions.
The paper shows optimal robustness against adversarial corruption in sequential decision-making problems.
problem Optimal robustness to adversarial corruption in online decision-making problems.
method Investigates prediction with expert advice and multi-armed bandit problems, focusing on algorithms with decreasing learning rates and second-order regret bounds.
result Optimal robustness can be expressed by a square-root dependency on the amount of corruption, achieving O ( log N Δ + C log N Δ ) O(\frac{\log N}{\Delta} + \sqrt{\frac{C \log N}{\Delta}}) O ( Δ l o g N + Δ C l o g N ) -regret. Robust VAE detects anomalies in corrupted data.
problem Detect anomalies in data with high corruption.
method Robust Variational Autoencoder (VAE) with four modifications.
result Establishes robustness to outliers and suitability to low-rank modeling.
Improved SGD for robust linear and ReLU regression with adversarial corruptions.
problem Robust regression with adversarial corruptions in streaming data.
method Stochastic gradient descent (SGD-exp) with exponentially decaying step size.
result Nearly linear convergence to true parameter with up to 50% Massart corruption rate.
New algorithm robustly trains deep neural networks under corrupted supervision.
problem Training deep neural networks with corrupted supervision data.
method Unified framework for classification and regression, focusing on collective impact of data points on average gradient.
result Achieves strong guarantees without assuming the type of corruption, robust under various types of corruption.
Robustly estimates mean with quantized data and corruption.
problem Mean estimation under quantization and adversarial corruption.
method Constructs multivariate robust estimators in two settings.
result Optimal estimators up to logarithmic factors.
Class selectivity affects robustness to corruptions but not to adversarial attacks.
problem Understanding the relationship between class selectivity and robustness in neural networks.
method Investigated the impact of class selectivity on robustness to natural corruptions and adversarial attacks using Tiny ImageNetC and CIFAR10C datasets.
result Decreasing class selectivity increases robustness to both natural corruptions and adversarial attacks.
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.
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…
Unified framework SVAM learns GLMs robustly to adversarial label corruption.
problem Learning GLMs under adversarial label corruption.
method SVAM framework based on variance reduction technique.
result Provable model recovery guarantees superior to state-of-the-art.
Efficient algorithm detects communities in noisy graphs with robustness.
problem Community detection in stochastic block models with adversarial corruptions.
method Efficient algorithm using semidefinite programming for robust clustering.
result Achieves error O ( ε ) + e − C 2 ( 1 ± o ( 1 ) ) O(ε) + e^{-\frac{C}{2} (1 \pm o(1))} O ( ε ) + e − 2 C ( 1 ± o ( 1 )) for ε ε ε -fraction of corruptions. New method improves neural network robustness without sacrificing generalization.
problem Robustness and generalization are often at odds in neural networks.
method Distributionally robust loss function bridging robustness and generalization.
result Certified robustness against data evasion and poisoning attacks with guaranteed generalization.
Picket guards against corrupted data in machine learning models.
problem Data corruption biases models and invalidates predictions.
method PicketNet detects corrupted data using self-supervised deep learning; flags corrupted queries online.
result Picket consistently protects models from corrupted data during training and deployment.
New algorithm robust to label corruptions in active learning.
problem Active learning under unknown adversarial label corruptions.
method Proposed a new active learning algorithm that is provably correct without assumptions on corruptions.
result Achieves minimax label complexity in non-corrupted setting and only requires additional labels to achieve desired accuracy in corrupted setting.
Robust Lasso-Zero handles missing covariates and sparse corruptions.
problem Sparse corruptions and missing covariates in sparse linear models.
method Extension of Lasso-Zero to handle sparse corruptions, with theoretical guarantees on sign recovery.
result Robust Lasso-Zero can handle missing values without specifying a parametric model.
Robust Q-learning algorithm resists corrupted rewards.
problem Non-ideal environments with corrupted rewards.
method Developed a novel robust Q-learning algorithm using historical data.
result Finite-time convergence rate matches state-of-the-art bounds.
Achieving robustness to distributional shift is a longstanding and challenging goal of computer vision. Data augmentation is a commonly used approach for improving robustness, however robustness gains are typically not uniform across corruption types. Indeed increasing performance in the presence of random noise is oft…
Gradient descent recovers low-rank matrices from corrupted measurements with double over-parameterization.
problem Robust recovery of low-rank matrices from grossly corrupted measurements.
method Gradient descent with discrepant learning rates for double over-parameterized models.
result Gradient descent with discrepant learning rates provably recovers the underlying matrix without prior knowledge on rank or sparsity.
Paper introduces robust deep learning method for handling random data corruption.
problem Random corruption in deep learning data due to limited quality of data.
method Inspired by median-of-means and Le Cam's principle, introduces a new approach.
result Demonstrates the approach performs well in practice and is a promising alternative to standard training methods.
New algorithm optimizes noisy, potentially corrupted functions.
problem Optimizing unknown functions with noisy bandit feedback, especially when evaluations are corrupted.
method Fast-Slow GP-UCB algorithm, combining robust and non-robust evaluations, enlarged confidence bounds.
result Theoretical analysis upper bounds cumulative regret, showing dependencies on corruption level and kernel.
Adversarial training improves robustness against common corruptions.
problem Improving robustness of models against common corruptions.
method Adversarial training with ℓ p \ell_p ℓ p perturbation and learned perceptual similarity. result Our approach leads to state-of-the-art performance on common corruptions.
New algorithm tackles adversarial corruption in Lipschitz bandits with sub-linear regret.
problem Adversarial corruption in Lipschitz bandits.
method Developed robust Lipschitz bandit algorithms for weak and strong adversaries.
result Achieved sub-linear regret under both weak and strong adversaries.
We consider the robust phase retrieval problem of recovering the unknown signal from the magnitude-only measurements, where the measurements can be contaminated by both sparse arbitrary corruption and bounded random noise. We propose a new nonconvex algorithm for robust phase retrieval, namely Robust Wirtinger Flow to …
Improved ε ε ε -greedy handles strategic bidding in PPC auctions.
problem Strategic bidding in PPC auctions with personalization and corruptions.
method Extended ε ε ε -greedy to handle strategic arms in contextual multi-arm bandit. result ε ε ε -greedy is robust to adversarial corruptions and degrades linearly with corruption. New methods tackle robust reinforcement learning in sparse, corrupted data.
problem Tackles robust reinforcement learning in sparse, corrupted data.
method Proposes actor-critic methods with sparse robust estimator oracles.
result First non-vacuous guarantees in high-dimensional sparse MDPs with single-policy concentrability coverage.
New algorithm optimizes robust estimation under mixed local and global corruptions.
problem Combining local and global corruptions in robust statistics.
method Information-theoretic approach using sliced-Wasserstein metric.
result Optimal error achieved in polynomial time for stronger local perturbations.
Enhances deep networks robustness with data mollification and label smoothing.
problem Improving deep neural networks' robustness against corruptions.
method Coupling data mollification (image noising and blurring) with label smoothing.
result Improved robustness and uncertainty quantification on corrupted image benchmarks.
New method tackles tensor regression with robust Kaczmarz approach.
problem Reconstructing tensor signals from corrupted measurements.
method Quantile-based randomized Kaczmarz method for tensor linear systems.
result Improved convergence and robustness to adversarial corruptions.