Abstract

Anomaly detection is a crucial task in various domains, including cybersecurity, healthcare, and finance, where identifying rare and abnormal events is of paramount importance. One-Class Classification (OCC) methods have emerged as a powerful approach for this task, effectively distinguishing between normal and anomalous data when only the normal class is well-represented. This paper provides a comprehensive review of OCC techniques, categorizing them into four main approaches: Reconstruction-Based Methods, Variational Autoencoders (VAEs), Convolutional Approaches, and Hybrid Models. Additionally, it delves into the diverse applications of OCC, including the detection of rare diseases in healthcare, financial fraud prevention, and industrial fault detection. The review also addresses key challenges such as data imbalance, model interpretability, and scalability, while highlighting recent trends and advancements in the field.

References

• S. Narasimhan and S. L. Shah, “Model identification and error covariance matrix estimation from noisy data using PCA,” Control Engineering Practice, vol. 16, no. 1, pp. 146–155, Jun. 2007.
• T. Kohonen, Self-Organizing Maps. 2001. doi: 10.1007/978-3-642-56927-2.
• F. Angiulli, F. Fassetti, and L. Ferragina, “Reconstruction Error-based Anomaly Detection with Few Outlying Examples,” arXiv.org, May 17, 2023.
• M. S. Battikh and A. A. Lenskiy, “Latent-Insensitive autoencoders for Anomaly Detection,” arXiv.org, Oct. 25, 2021.
• J. Lu, W. Li, and Y. Zhao, “Reconstruction-Based One-Class classification anomaly detection for tabular data,” in Communications in computer and information science, 2022, pp. 313–326. doi: 10.1007/978-981-19-4109-2_29.
• F. Liu, X. Zhu, P. Feng, and L. Zeng, “Anomaly detection via progressive reconstruction and hierarchical feature fusion,” Sensors, vol. 23, no. 21, p. 8750, Oct. 2023, doi: 10.3390/s23218750.
• M. Salehi et al., “ARAE: Adversarially robust training of autoencoders improves novelty detection,” Neural Networks, vol. 144, pp. 726–736, Sep. 2021, doi: 10.1016/j.neunet.2021.09.014.
• An, Jinwon and Sungzoon Cho. “Variational Autoencoder based Anomaly Detection using Reconstruction Probability.” (2015).
• C. Zhang et al., “VESC: a new variational autoencoder based model for anomaly detection,” International Journal of Machine Learning and Cybernetics, vol. 14, no. 3, pp. 683–696, Oct. 2022, doi: 10.1007/s13042-022-01657-w.
• N. Najari, S. Berlemont, G. Lefebvre, S. Duffner, and C. Garcia, “Robust variational autoencoders and normalizing flows for unsupervised network anomaly detection,” in Lecture notes in networks and systems, 2022, pp. 281–292. doi: 10.1007/978-3-030-99587-4_24.
• C. Zhang, S. Li, H. Zhang, and Y. Chen, “VELC: a new variational AutoEncoder based model for Time Series anomaly detection,” arXiv.org, Jul. 03, 2019.
• “OC-FakeDECT: Classifying deepfakes using one-class variational autoencoder,” IEEE Conference Publication | IEEE Xplore, Jun. 01, 2020.
• Daehyung Park, Yuuna Hoshi, and Charles C Kemp. 2018. A multimodal anomaly detector for robot-assisted feeding using an lstm-based variational autoencoder. IEEE Robotics and Automation Letters 3, 3 (2018), 1544–1551.
• F. Laakom, F. Sohrab, J. Raitoharju, A. Iosifidis, and M. Gabbouj, “Convolutional autoencoder-based multimodal one-class classification,” arXiv.org, Sep. 25, 2023.
• “One-Class Learned Encoder-Decoder Network with Adversarial Context Masking for Novelty Detection,” IEEE Conference Publication | IEEE Xplore, Jan. 01, 2022.
• R. Chalapathy, A. K. Menon, and S. Chawla, “Anomaly Detection using One-Class Neural Networks,” arXiv.org, Feb. 18, 2018.
• P. Oza and V. M. Patel, “One-Class Convolutional Neural Network,” IEEE Signal Processing Letters, vol. 26, no. 2, pp. 277–281, Feb. 2019, doi: 10.1109/lsp.2018.2889273.
• P. Liznerski, L. Ruff, R. A. Vandermeulen, B. J. Franks, M. Kloft, and K.-R. Müller, “Explainable deep One-Class classification,” arXiv.org, Jul. 03, 2020.
• I. T. Nicholaus, J.-S. Lee, and D.-K. Kang, “One-Class convolutional neural networks for Water-Level anomaly detection,” Sensors, vol. 22, no. 22, p. 8764, Nov. 2022, doi: 10.3390/s22228764.
• Z. Zhang, B. Patel, B. Patel, and I. Banerjee, “Unsupervised Hybrid framework for ANomaly Detection (HAND) -- applied to Screening Mammogram,” arXiv.org, Sep 2024.
• L. Ruff et al., “Deep One-Class Classification,” PMLR, Jul. 03, 2018.
• Y. Chen, Y. Tian, G. Pang, and G. Carneiro, “Deep One-Class Classification via Interpolated Gaussian Descriptor”, AAAI, vol. 36, no. 1, pp. 383-392, Jun. 2022.
• D. M. J. Tax and R. P. W. Duin, “Combining One-Class classifiers,” in Lecture notes in computer science, 2001, pp. 299–308. doi: 10.1007/3-540-48219-9_30.
• B. Krawczyk, M. Woźniak, and B. Cyganek, “Clustering-based ensembles for one-class classification,” Information Sciences, vol. 264, pp. 182–195, Jan. 2014, doi: 10.1016/j.ins.2013.12.019.
• K. Demertzis, L. Iliadis, and S. Spartalis, “A spiking One-Class anomaly detection framework for Cyber-Security on industrial control systems,” in Communications in computer and information science, 2017, pp. 122–134. doi: 10.1007/978-3-319-65172-9_11.
• E. Šabić, D. Keeley, B. Henderson, and S. Nannemann, “Healthcare and anomaly detection: using machine learning to predict anomalies in heart rate data,” AI & Society, vol. 36, no. 1, pp. 149–158, May 2020, doi: 10.1007/s00146-020-00985-1.
• N. Seliya, A. A. Zadeh, and T. M. Khoshgoftaar, “A literature review on one-class classification and its potential applications in big data,” Journal of Big Data, vol. 8, no. 1, Sep. 2021, doi: 10.1186/s40537-021-00514-x.
• P. Zheng, S. Yuan, X. Wu, J. Li, and A. Lu, “One-Class adversarial nets for fraud detection,” Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, no. 01, pp. 1286–1293, Jul. 2019, doi: 10.1609/aaai.v33i01.33011286.
• P. Perera, P. Oza, and V. M. Patel, “One-Class Classification: a survey,” arXiv.org, Jan. 08, 2021. https://arxiv.org/abs/2101.03064
• P. Perera, R. Nallapati, and B. Xiang, “OCGAN: One-class Novelty Detection Using GANs with Constrained Latent Representations,”, CVPR, Mar. 20, 2019.
• H. Gao, H. Luo, F. Shen, and Z. Zhang, “Exploring the optimization objective of One-Class classification for anomaly detection,” arXiv.org, Aug. 23, 2023.
• G. Michau and O. Fink, “Domain adaptation for One-Class classification: Monitoring the health of critical systems under limited information,” International Journal of Prognostics and Health Management, vol. 10, no. 4, Dec. 2019, doi: 10.36001/ijphm.2019.v10i4.2613.
• X. Wang, B. Jin, Y. Du, P. Cui, Y. Tan, and Y. Yang, “One-class graph neural networks for anomaly detection in attributed networks,” Neural Computing and Applications, vol. 33, no. 18, pp. 12073–12085, Mar. 2021, doi: 10.1007/s00521-021-05924-9.
• A. Oladosu et al., “Meta-Learning for One-Class Classification with Few Examples using Order-Equivariant Network,” arXiv.org, Jul. 08, 2020. https://arxiv.org/abs/2007.04459