Detects spiky corruption in CRMDPs to learn optimal policies.
problem Learning optimal policies in environments with imperfect reward functions.
method Characterized spiky reward corruption, introduced algorithm to detect corrupt states.
result Algorithm can detect corrupt states and learn optimal policies.
Benchmark improves object detection robustness in winter weather.
problem Assessing object detection models' performance under image corruptions.
method Developed three benchmark datasets with various image corruptions; used data augmentation to improve robustness.
result Simple data augmentation significantly enhances model robustness across different corruptions and datasets.
Automated graphics testing detects novel corruptions without manual labeling.
problem Detecting novel visual corruptions in graphics unit testing without manual labeling.
method Reproduces driver bugs to generate corruptions and uses Multiple Instance Learning (MIL) methods.
result Significantly outperforms unsupervised methods and discovers novel corruptions.
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.
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 detects communities even with corrupted data, reaching Kesten-Stigum threshold.
problem Robust community detection in stochastic block model with node corruptions.
method Polynomial-time algorithm using Grothendieck norm of principal submatrices.
result First algorithm to achieve weak recovery at Kesten-Stigum threshold with node corruptions.
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.
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−2C(1±o(1)) for ε-fraction of corruptions. Algorithm detects corrupted data using gradient descent.
problem Detecting mislabeled samples in noisy training datasets.
method Optimizing network performance on clean validation set via gradient descent.
result Algorithm improves network performance on validation set.
DynaCor detects noisy labels by learning from corrupted training signals.
problem Label noise in real-world datasets hinders model generalization.
method DynaCor introduces label corruption to indirectly simulate noisy labels and learns to distinguish clean from noisy instances.
result DynaCor outperforms state-of-the-art competitors in noisy label detection.
We introduce a comprehensive and statistical framework in a model free setting for a complete treatment of localized data corruptions due to severe noise sources, e.g., an occluder in the case of a visual recording. Within this framework, we propose i) a novel algorithm to efficiently separate, i.e., detect and localiz…
The paper proposes a method to detect and filter noisy or mislabeled data using pointwise mutual information.
problem Detecting and filtering noisy or mislabeled data in deep learning models.
method A mutual information-based framework quantifying statistical dependencies between inputs and labels.
result The method effectively filters low-quality samples, improving classification accuracy by up to 15%.
MimicGAN improves robustness of image projections under corruption.
problem Robust projection onto image manifolds is challenging due to corruptions.
method Proposes corruption mimicking to robustly project images.
result Significantly more robust than PGD under various corruptions.
Analyzes biased random walks and corrupted intervals in adversarial settings.
problem Learning thresholds and intervals in adversarial conditions.
method Analyzes biased random walks and corrupted intervals under adversarial design.
result Analyzes the expected behavior of biased random walks and corrupted intervals.
Subsampling methods have been recently proposed to speed up least squares estimation in large scale settings. However, these algorithms are typically not robust to outliers or corruptions in the observed covariates. The concept of influence that was developed for regression diagnostics can be used to detect such corrup…
RVAE detects and repairs corrupted cells in mixed-type tabular data.
problem Outlier detection and repair in mixed-type tabular data.
method Robust Variational Autoencoder (RVAE) learns the joint distribution of clean data and identifies outlier cells.
result RVAE outperforms state-of-the-art methods in cell outlier detection and repair for tabular data.
New method detects anomalies without bias, improving on autoencoder reconstruction errors.
problem Inherent biases in autoencoder-based anomaly detection methods.
method Introduces a Lipschitz anomaly discriminator trained to detect differences between training data and corruptions.
result Successfully detects anomalies with guarantees on certain Wasserstein distances.
Novel method solves group synchronization with robust corruption tolerance.
problem Group synchronization with high corruption tolerance.
method Quadratic programming formulation exploiting cycle consistency.
result Global minimum recovers corruption levels under mild conditions.
Dynamic Influence Tracker measures changing sample importance during model training.
problem Static influence measurements during training overlook how sample importance varies over time.
method Dynamic Influence Tracker (DIT) captures time-varying sample influence across arbitrary time windows.
result DIT reveals distinct learning phases with shifting priorities and detects corrupted samples more efficiently.
In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the generalization error of the classifier on non-corrupted measurements while controlling th…
In this paper, we propose a general framework to learn a robust large-margin binary classifier when corrupt measurements, called anomalies, caused by sensor failure might be present in the training set. The goal is to minimize the generalization error of the classifier on non-corrupted measurements while controlling th…
A new method combines generative and feature-based approaches for unsupervised anomaly detection.
problem Identifying subtle anomalies in test samples compared to a normative distribution.
method A generative cold-diffusion pipeline trained to restore synthetically-corrupted images, combined with a novel synthetic anomaly generation procedure and ensembling restorations.
result Surpasses prior state-of-the-art for unsupervised anomaly detection in three Brain MRI datasets.
Improved OOD detection across various shifts using multi-encoder fusion of RDMs.
problem Out-of-distribution detection across multiple types of distribution shifts.
method Statistical identification of encoder sensitivity, EncMin2L fusion, and Tippett minimum combination.
result Achieves AUROC ≥ 0.94 across four shift types, outperforming state-of-the-art detectors.
SPECTRE defends against backdoor attacks by amplifying corrupted data's spectral signature.
problem Backdoor attacks that change model behavior with specific triggers.
method Robust covariance estimation to amplify spectral signature of poisoned data.
result Clean model is completely removed from backdoor, even in hard-to-detect cases.
Self-supervised learning enhances model robustness and uncertainty.
problem Improving model robustness and uncertainty estimation.
method Self-supervised learning without requiring labels.
result Self-supervised learning improves robustness to adversarial examples, label corruption, and input corruptions.
Detects corruption in agentic models during execution.
problem Inconsistent context, retrieval errors, or adversarial inputs corrupt intermediate steps of reasoning chains.
method Analyzes token graphs induced by attention and computes spectral statistics to emit accept/reject signals.
result A single threshold on the high frequency energy ratio optimally detects context inconsistency in agentic models.
The paper addresses bias in fraud detection models by improving label recovery in payment networks.
problem Systematic bias in chargeback labels in payment networks.
method Formalizes the observation pipeline as a sequential missing-data problem with three stages and a corruption layer. Constructs the Sequential Triply Robust (STR) estimator to correct for all four impairments simultaneously.
result Achieves the semiparametric efficiency bound and provably dominates naive chargeback-based training in mean squared error.
Subspace recovery from corrupted and missing data is crucial for various applications in signal processing and information theory. To complete missing values and detect column corruptions, existing robust Matrix Completion (MC) methods mostly concentrate on recovering a low-rank matrix from few corrupted coefficients w…
PCA is a classical statistical technique whose simplicity and maturity has seen it find widespread use as an anomaly detection technique. However, it is limited in this regard by being sensitive to gross perturbations of the input, and by seeking a linear subspace that captures normal behaviour. The first issue has bee…
The positive-unlabeled (PU) classification is a common scenario in real-world applications such as healthcare, text classification, and bioinformatics, in which we only observe a few samples labeled as "positive" together with a large volume of "unlabeled" samples that may contain both positive and negative samples. Bu…
Anomaly detection is the process of finding data points that deviate from a baseline. In a real-life setting, anomalies are usually unknown or extremely rare. Moreover, the detection must be accomplished in a timely manner or the risk of corrupting the system might grow exponentially. In this work, we propose a two lev…
Traditional multi-view learning approaches suffer in the presence of view disagreement,i.e., when samples in each view do not belong to the same class due to view corruption, occlusion or other noise processes. In this paper we present a multi-view learning approach that uses a conditional entropy criterion to detect v…
Paper develops a method to robustly cluster tensors with outliers.
problem Clustering tensors contaminated by outliers or sample-specific corruptions.
method Transformed Tensor Low-Rank Representation (OR-TLRR) method.
result Provably recovers row space of clean data and detects outliers.
A robust loss for anomaly mitigation and unsupervised contamination classification
problem Detecting and mitigating contamination in supervised and unsupervised settings
method Neural Bayesian Anomaly Mitigation (NBAM)
result Recovering the structure of contamination and identifying label-flip pairs
We investigate conditions under which test statistics exist that can reliably detect examples, which have been adversarially manipulated in a white-box attack. These statistics can be easily computed and calibrated by randomly corrupting inputs. They exploit certain anomalies that adversarial attacks introduce, in part…
We study high-dimensional distribution learning in an agnostic setting where an adversary is allowed to arbitrarily corrupt an ε-fraction of the samples. Such questions have a rich history spanning statistics, machine learning and theoretical computer science. Even in the most basic settings, the only known…
New taxonomy reveals different detection limits for various types of fraud.
problem Existing fraud detection treats all fraud as the same, ignoring its diverse forms.
method Introduced an observation-mechanism taxonomy with five fraud classes.
result Separate estimation by fraud class outperforms pooled estimation.
Robust VAE improves model performance on corrupted data.
problem Outliers in training data degrade model performance.
method Applying robust statistics to VAEs using beta-divergence.
result Improved robustness to outliers in generated representations.
Optimizes variational autoencoder for detecting missing data in Mars rover transmissions.
problem Detecting missing data in Mars rover transmissions to prevent volume loss and corruption.
method Applies derivative-free optimization to tune variational autoencoder.
result Improves variational autoencoder's ability to detect missing data, aiding GDSA team.
New method for robust PCA with exponential family distributions.
problem Recovering low-rank structure from data matrices with outliers.
method Alternating Direction Method of Multipliers for eextRPCA. result Demonstrated effectiveness in steel sheet defect detection and crime activity monitoring.
Develops a comprehensive theory of corruption in supervised learning.
problem Widespread corruption in data collection affects supervised learning problems.
method Introduces a general theory of corruption using Markov kernels, distinguishing and comparing corruption types.
result Establishes a unified framework for corruption types and develops mitigation strategies.
A new algorithm detects out-of-distribution samples by concentrating them in feature space.
problem Building safe AI systems requires effective out-of-distribution detection.
method The paper proposes a novel algorithm based on the observation that OoD samples concentrate in feature space.
result The algorithm achieves state-of-the-art performance on various OoD detection benchmarks.
Paper tackles anomaly detection in SAR images without labeled data.
problem Anomaly detection in SAR images with speckle noise and spatial correlation issues.
method Self-supervised deep learning approach: despeckling, adversarial autoencoder, change detection.
result Method outperforms conventional algorithms in detecting anomalies in SAR images.
Patch Gaussian augmentation improves model robustness without sacrificing accuracy.
problem Challenges in building robust models without sacrificing accuracy.
method Adds Gaussian noise to randomly selected patches in images.
result Achieves state-of-the-art performance on benchmarks while improving clean data accuracy.
Method detects errors in numerical data using regression models.
problem Noise and errors in numerical datasets.
method Introduced veracity scores and a filtering procedure for error detection.
result Method outperforms other approaches in identifying incorrect values.
BeGIN benchmarks GNNs for instance-dependent label noise in graphs.
problem Instance-dependent label noise in graph data.
method BeGIN introduces a benchmark with various noise types and evaluates noise-handling strategies across GNN architectures.
result Challenges of instance-dependent noise, especially LLM-based corruption, and the importance of node-specific parameterization.
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.
Study finds corruption negatively impacts firm performance.
problem The impact of corruption on firm performance is examined.
method Cross-sectional data analysis of a large international dataset.
result Corruption negatively affects corporate performance.