Improves interpretability of anomaly scores in GBRBM-based detection.
problem Difficulty in setting a proper threshold for anomaly scores.
method Proposes a measure based on cumulative distribution and uses simulated annealing for evaluation.
result Established a guideline for setting the threshold using the interpretable measure.
OMASGAN generates anomalous samples on distribution boundary to improve anomaly detection.
problem Missed anomalies and low AD performance due to OoD samples in generative models.
method OMASGAN generates anomalous samples on the estimated distribution boundary using a GAN approach, refining AD models.
result OMASGAN improves AD performance by at least 0.24 and 0.07 points on average on MNIST and CIFAR-10 datasets.
We propose a non-parametric anomaly detection algorithm for high dimensional data. We first rank scores derived from nearest neighbor graphs on n-point nominal training data. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as…
Anomaly detection aims to detect abnormal events by a model of normality. It plays an important role in many domains such as network intrusion detection, criminal activity identity and so on. With the rapidly growing size of accessible training data and high computation capacities, deep learning based anomaly detection…
We propose a non-parametric anomaly detection algorithm for high dimensional data. We score each datapoint by its average K-NN distance, and rank them accordingly. We then train limited complexity models to imitate these scores based on the max-margin learning-to-rank framework. A test-point is declared as an anomaly…
A new method assigns anomaly scores to features for better interpretation.
problem Interpreting anomaly scores from feature attributions.
method Proposes a characteristic function to attribute anomaly scores using Shapley value.
result Demonstrates the potential utility of the proposed attribution methods.
A new method optimizes anomaly scoring from score distribution to improve AD performance.
problem Vulnerability to anomaly contamination and lack of adaptability in existing AD methods.
method Optimizes anomaly scoring function from score distribution perspective, using Overlap loss.
result Overlap loss-based AD models significantly outperform state-of-the-art methods.
Although deep learning has been applied to successfully address many data mining problems, relatively limited work has been done on deep learning for anomaly detection. Existing deep anomaly detection methods, which focus on learning new feature representations to enable downstream anomaly detection methods, perform in…
Use of an autoencoder (AE) as a normal model is a state-of-the-art technique for unsupervised-anomaly detection in sounds (ADS). The AE is trained to minimize the sample mean of the anomaly score of normal sounds in a mini-batch. One problem with this approach is that the anomaly score of rare-normal sounds becomes hig…
Proposes a method to measure similarity between anomaly scores from different methods.
problem Difficulty in directly comparing anomaly detection methods.
method A measure based on extremal similarity in scoring distributions using a novel upper quadrant modeling approach.
result Demonstrates the ability to detect clusters of anomaly detection algorithms and achieve an accurate ensemble algorithm.
Improves anomaly detection with contaminated unlabeled data.
problem Weakness in existing semi-supervised anomaly detection methods when unlabeled data contain anomalies.
method Integrates positive-unlabeled learning with deep anomaly detection models.
result Achieves better detection performance on various datasets.
This paper evaluates anomaly detection methods for multivariate time series data.
problem Lack of systematic comparison of anomaly detection methods on multivariate time series data.
method Comprehensive evaluation of 10 models and 4 scoring functions on 10 datasets.
result Dynamic scoring functions outperform static ones, and the choice of scoring functions matters more than the model choice.
Topological anomaly scores predict return curves in S&P 500 stocks
problem Detecting anomalies in financial time series
method BallMapper, decoder-conditional VAE, Function-on-Function regression
result Anomaly history carries predictive content for return curves
We propose a supervised anomaly detection method for data with inexact anomaly labels, where each label, which is assigned to a set of instances, indicates that at least one instance in the set is anomalous. Although many anomaly detection methods have been proposed, they cannot handle inexact anomaly labels. To measur…
FAMDAD detects anomalies in mixed data using kurtosis-weighted Factor Analysis.
problem Detecting anomalies in high-dimensional mixed data.
method kurtosis-weighted Factor Analysis of Mixed Data (FAMDAD).
result Anomalies are highly separable in the first and last few dimensions of the FAMDAD embedding.
A new model combines VAE and GAN for better anomaly detection in imbalanced datasets.
problem Anomaly detection in imbalanced datasets, especially in medical applications.
method β-VAEGAN model combining VAE and GAN, kernelized SVM for anomaly scores, and deviation from Gaussian prior.
result Improved F1 score from 0.85 to 0.92 on MITBIH Arrhythmia Database. MIAEAD detects anomalies in mixed data types.
problem Challenges of heterogeneity in feature subsets for anomaly detection.
method Multiple-Input Variational Auto-Encoder (MIVAE) for simultaneous feature subset anomaly scoring.
result MIVAE outperforms conventional methods and state-of-the-art unsupervised models in AUC score.
Mitigates anomaly score imbalance in long-tailed distributions.
problem Class imbalance in normal data leads to skewed anomaly detection performance.
method Proposes an importance-weighted loss function to balance anomaly scores.
result Improves anomaly detection performance by 0.043 on real-world datasets.
Proposes BA method for unbiased time series anomaly detection evaluation.
problem Anomalies in time series data are rare, making F1-score unreliable.
method Introduces Balanced Point Adjustment (BA) to address F1-score bias.
result BA provides fairer evaluation of time series anomaly detectors.
This paper aims at formulating the issue of ranking multivariate unlabeled observations depending on their degree of abnormality as an unsupervised statistical learning task. In the 1-d situation, this problem is usually tackled by means of tail estimation techniques: univariate observations are viewed as all the more …
EHBOS enhances HBOS by capturing feature interactions, improving anomaly detection.
problem Limited ability of HBOS to detect anomalies in datasets with feature interactions.
method Incorporates two-dimensional histograms to capture feature pair dependencies.
result EHBOS outperforms HBOS on datasets with critical feature interactions, achieving notable improvements in ROC AUC.
Paper tackles anomaly detection with missing causal knowledge.
problem Detect anomalies with missing structural knowledge.
method Simple, efficient methods for polytree causal graphs.
result Heuristic identifies root causes based on anomaly scores.
TadGAN detects anomalies in time series data using GANs and LSTM.
problem Challenges in detecting anomalies in time series data, especially without labeled data.
method TadGAN uses Generative Adversarial Networks (GANs) with LSTM Recurrent Neural Networks to capture temporal correlations and compute anomaly scores.
result TadGAN outperforms 8 baseline methods in most cases, achieving the highest averaged F1 score.
Proposes a new model for online anomaly detection in multivariate time series.
problem Inaccurate anomaly detection in multivariate time series due to spurious correlations and lack of temporal causality.
method Clusters channels based on correlations, embeds each cluster, and integrates information through a causal mixer while maintaining temporal causality.
result Consistently superior performance across six public benchmark datasets.
Accurate and automated detection of anomalous samples in a natural image dataset can be accomplished with a probabilistic model for end-to-end modeling of images. Such images have heterogeneous complexity, however, and a probabilistic model overlooks simply shaped objects with small anomalies. This is because the proba…
Most current clustering based anomaly detection methods use scoring schema and thresholds to classify anomalies. These methods are often tailored to target specific data sets with "known" number of clusters. The paper provides a streaming clustering and anomaly detection algorithm that does not require strict arbitrary…
Correlated anomaly detection (CAD) from streaming data is a type of group anomaly detection and an essential task in useful real-time data mining applications like botnet detection, financial event detection, industrial process monitor, etc. The primary approach for this type of detection in previous researches is base…
Improves relevancy of black-box anomaly detectors with user feedback.
problem Users often ignore many detected anomalies, requiring a method to identify and prioritize relevant ones.
method Uses user feedback to adjust anomaly selection process based on identified anomaly types.
result Significant improvements in precision and recall over various anomaly detectors.
Through training on unlabeled data, anomaly detection has the potential to impact computer-aided diagnosis by outlining suspicious regions. Previous work on deep-learning-based anomaly detection has primarily focused on the reconstruction error. We argue instead, that pixel-wise anomaly ratings derived from a Variation…
Novel framework for contextual anomaly detection models uncertainty.
problem Identifying anomalies in target variables influenced by contextual variables.
method Normalcy score (NS) framework using heteroscedastic Gaussian process regression.
result NS outperforms state-of-the-art methods in detection accuracy and interpretability.
DTOR explains anomalies with rule-based explanations.
problem Need to explain anomalies in data effectively.
method Applies Decision Tree Regressor to estimate anomaly scores and generate rule-based explanations.
result DTOR produces robust and consistent rule-based explanations.
Real-time anomaly detection for edge streams using MIDAS and MIDAS-F.
problem Detecting unusual behavior in dynamic graph edge streams.
method MIDAS-F focuses on microcluster anomalies, incorporating anomalies into internal states to reduce poisoning effect.
result MIDAS-F outperforms MIDAS in accuracy, with up to 62% higher ROC-AUC.
CCE improves anomaly detection metrics by measuring both confidence and consistency.
problem Existing anomaly detection metrics lack discriminative power, hyperparameter dependency, and robustness to perturbations.
method CCE uses Bayesian estimation to quantify uncertainty and constructs global and event-level confidence and consistency scores.
result CCE demonstrates strict boundedness, robustness, and linear time complexity.
We propose a novel non-parametric adaptive anomaly detection algorithm for high dimensional data based on rank-SVM. Data points are first ranked based on scores derived from nearest neighbor graphs on n-point nominal data. We then train a rank-SVM using this ranked data. A test-point is declared as an anomaly at alpha-…
Bayesian method estimates contamination factor for unsupervised anomaly detection.
problem No good methods for estimating contamination factor in unsupervised anomaly detection.
method Bayesian approach using mixture formulation of anomaly detector outputs.
result Estimated contamination factor distribution is well-calibrated and improves anomaly detection performance.
Two new scoring methods improve anomaly detection in Isolation Forest.
problem Anomaly and outlier detection in data.
method Generalized score function and volume-based scoring for individual trees.
result Significant improvement in anomaly detection on 34 datasets.
Python package 'nonconform' simplifies conformal anomaly detection.
problem Heuristic thresholding in anomaly detection systems.
method 'nonconform' package converts anomaly scores into calibrated p-values.
result Statistically principled anomaly detection is made accessible.
Machine-learned anomaly detection in new-physics searches needs calibration and look-elsewhere correction
problem Machine-learned anomaly detection in new-physics searches
method Conformal prediction layer
result Calibrated significance with distribution-free guarantees
Graph regularized autoencoder improves anomaly detection performance.
problem Unsupervised anomaly detection in high-dimensional data.
method Developed a graph regularized autoencoder using MST-based distances.
result Outperforms alternative methods on 20 benchmark anomaly detection datasets.
A new method for detecting anomalies in large, high-dimensional data streams using probabilistic forest models.
problem Challenges in detecting anomalies in large, high-dimensional data.
method Probabilistic Mondrian Pólya Forests for summarizing data and estimating underlying probability density.
result State-of-the-art performance with interpretable anomaly scores.
Anomalies (unusual patterns) in time-series data give essential, and often actionable information in critical situations. Examples can be found in such fields as healthcare, intrusion detection, finance, security and flight safety. In this paper we propose new conformalized density- and distance-based anomaly detection…
Anomaly detection is a classical but worthwhile problem, and many deep learning-based anomaly detection algorithms have been proposed, which can usually achieve better detection results than traditional methods. In view of reconstruct ability of the model and the calculation of anomaly score, this paper proposes a time…
We tackle anomaly detection in sparse time series data.
problem Sparse time series with low signal-to-noise ratios and non-uniform performance.
method We introduce a novel generative procedure for benchmark datasets and demonstrate how anomaly score smoothing improves performance.
result Anomaly score smoothing consistently improves performance in low-count time series anomaly detection.
Trimming helps in conformal prediction when it separates anomaly scores.
problem Effectiveness of trimming in conformal prediction under contamination.
method Analyse fixed-threshold trimming as a replacement of the contaminated calibration law with a retained law.
result Trimming helps when it separates anomaly scores, reducing clean-target coverage to a one-dimensional score-CDF transfer problem.
New approach uses loss functions to extend data depth for anomaly detection.
problem Anomaly detection in high-dimensional data.
method Introducing loss depths to generalize halfspace depth.
result New loss depths improve anomaly detection efficiency and interpretability.
Reconstruction error is a prevalent score used to identify anomalous samples when data are modeled by generative models, such as (variational) auto-encoders or generative adversarial networks. This score relies on the assumption that normal samples are located on a manifold and all anomalous samples are located outside…
We present an extension to the model-free anomaly detection algorithm, Isolation Forest. This extension, named Extended Isolation Forest (EIF), resolves issues with assignment of anomaly score to given data points. We motivate the problem using heat maps for anomaly scores. These maps suffer from artifacts generated by…
Proposes a method to detect anomalies in financial time series using PCA and neural networks.
problem Anomalies in financial time series lead to miscalibrated risk models.
method Extract features using PCA, define anomaly score with neural network, calibrate cutoff value.
result The proposed PCA NN approach outperforms other anomaly detection methods.