mlsanityData to 14 Oct 2026

Perturbation Learning Based Anomaly Detection

arXiv 2206.02704 ↗First posted 6 Jun 2022cs.LG cs.AIcited by 24

Not on the map. Why?

Abstract (arXiv)

This paper presents a simple yet effective method for anomaly detection. The main idea is to learn small perturbations to perturb normal data and learn a classifier to classify the normal data and the perturbed data into two different classes. The perturbator and classifier are jointly learned using deep neural networks. Importantly, the perturbations should be as small as possible but the classifier is still able to recognize the perturbed data from unperturbed data. Therefore, the perturbed data are regarded as abnormal data and the classifier provides a decision boundary between the normal data and abnormal data, although the training data do not include any abnormal data. Compared with the state-of-the-art of anomaly detection, our method does not require any assumption about the shape (e.g. hypersphere) of the decision boundary and has fewer hyper-parameters to determine. Empirical studies on benchmark datasets verify the effectiveness and superiority of our method.

Key facts. Cited by 24 papers in the map (data through 14 Oct 2026). Builds on 19 of its 48 references that are in the map. First posted on arXiv 6 Jun 2022.

Builds on

19 of 48 references.

References · 19

  1. 2017Attention Is All You Needcited by 60,361
  2. 2014Adam: A Method for Stochastic Optimizationcited by 37,240
  3. 2013Auto-Encoding Variational Bayescited by 4,053
  4. 2018Deep Clustering for Unsupervised Learning of Visual Featurescited by 1,028
  5. 2020A Unifying Review of Deep and Shallow Anomaly Detectioncited by 425
  6. 2019Deep Semi-Supervised Anomaly Detectioncited by 291
  7. 2018Deep Anomaly Detection Using Geometric Transformationscited by 269
  8. 2016LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detectioncited by 215
  9. 2020Classification-Based Anomaly Detection for General Datacited by 211
  10. 2019OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representationscited by 199
  11. 2018Latent Space Autoregression for Novelty Detectioncited by 149
  12. 2020DROCC: Deep Robust One-Class Classificationcited by 121
7 more
  1. 2018Generative Probabilistic Novelty Detection with Adversarial Autoencoderscited by 99
  2. 2021Neural Transformation Learning for Deep Anomaly Detection Beyond Imagescited by 99
  3. 2020A Survey of Single-Scene Video Anomaly Detectioncited by 88
  4. 2018Learning Deep Features for One-Class Classificationcited by 76
  5. 2021Deep One-Class Classification via Interpolated Gaussian Descriptorcited by 67
  6. 2020A General Framework For Detecting Anomalous Inputs to DNN Classifierscited by 24
  7. 2019Deep Anomaly Detection for Generalized Face Anti-Spoofingcited by 17

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 1; 2023: 6; 2024: 3; 2025: 11; 2026: 3.

24 papers.

Sort:

By area:

  1. 2024ARC: A Generalist Graph Anomaly Detector with In-Context Learningcited by 48
  2. 2022Calibrated One-class Classification for Unsupervised Time Series Anomaly Detectioncited by 40
  3. 2024GeneralAD: Anomaly Detection Across Domains by Attending to Distorted Featurescited by 29
  4. 2024Generative Semi-supervised Graph Anomaly Detectioncited by 22
  5. 2023NNG-Mix: Improving Semi-supervised Anomaly Detection with Pseudo-anomaly Generationcited by 14
  6. 2023Deep Orthogonal Hypersphere Compression for Anomaly Detectioncited by 12
  7. 2023PseudoBound: Limiting the anomaly reconstruction capability of one-class classifiers using pseudo anomaliescited by 8
  8. 2025Anomaly Detection and Generation with Diffusion Models: A Surveycited by 8
  9. 2025Adaptive Multi-prompt Contrastive Network for Few-shot Out-of-distribution Detectioncited by 8
  10. 2025Scale-Aware Contrastive Reverse Distillation for Unsupervised Medical Anomaly Detectioncited by 6
  11. 2025Subject Information Extraction for Novelty Detection with Domain Shiftscited by 6
  12. 2023Unilaterally Aggregated Contrastive Learning with Hierarchical Augmentation for Anomaly Detectioncited by 5
12 more
  1. 2023Restricted Generative Projection for One-Class Classification and Anomaly Detectioncited by 2
  2. 2025Removing Geometric Bias in One-Class Anomaly Detection with Adaptive Feature Perturbationcited by 2
  3. 2026Interpretable Maximum Margin Deep Anomaly Detectioncited by 2
  4. 2025Multi-Relation Graph-Kernel Strengthen Network for Graph-Level Clusteringcited by 1
  5. 2025Fairness-aware Anomaly Detection via Fair Projectioncited by 1
  6. 2025Text-ADBench: Text Anomaly Detection Benchmark Based on LLM Embeddingscited by 1
  7. 2023AnoRand: A Semi Supervised Deep Learning Anomaly Detection Method by Random Labelingcited by 0
  8. 2025Dual Boost-Driven Graph-Level Clustering Networkcited by 0
  9. 2025Bridging Unsupervised and Semi-Supervised Anomaly Detection: A Theoretically-Grounded and Practical Framework with Synthetic Anomaliescited by 0
  10. 2025UniOD: A Universal Model for Outlier Detection across Diverse Domainscited by 0
  11. 2026Make Some Noise: Unsupervised Remote Sensing Change Detection Using Latent Space Perturbationscited by 0
  12. 2026Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generationcited by 0