Enhancing Anomaly Detection Through Latent Space Manipulation in Autoencoders: A Comparative Analysis
Source abstract
Abstract
This article explores the practical implementation of autoencoders for anomaly detection, emphasizing their latent space manipulation and applicability across various domains. This study highlights the impact of optimizing parameter configurations, lightweight architectures, and training methodologies to enhance anomaly detection performance. A comparative analysis of autoencoders, Variational Autoencoders, and their modified counterparts was conducted within a tailored experimental environment designed to simulate real-world scenarios. The results demonstrate that these models, when fine-tuned, achieve significant improvements in detection accuracy, specificity, and sensitivity while maintaining computational efficiency. The findings underscore the importance of lightweight, practical models and the integration of streamlined training processes in developing effective anomaly detection systems. This study provides valuable insights into advancing machine learning methods for real-world applications and sets the stage for further refinement of autoencoder-based approaches.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Anomaly Detection Techniques and Applications · Network Security and Intrusion Detection · Time Series Analysis and Forecasting
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Electronics, Military University of Technology, Electronics and Telecommunications, 00-908 Warszawa, Poland
Funding
Military University of Technology
References (63)
Show source-provided references
1. Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances10.1016/j.eswa.2021.116429 ↗
2. A Survey of Anomaly Detection Techniques in Financial Domain10.1016/j.future.2015.01.001 ↗
3. Elliott, A., Cucuringu, M., Luaces, M.M., Reidy, P., and Reinert, G. (2019). Anomaly Detection in Networks with Application to Financial Transaction Networks. arXiv.
4. Literature Review: Anomaly Detection Approaches on Digital Business Financial Systems10.1016/j.digbus.2022.100038 ↗
5. Ukil, A., Bandyoapdhyay, S., Puri, C., and Pal, A. (2016, January 23–25). IoT Healthcare Analytics: The Importance of Anomaly Detection. Proceedings of the 2016 IEEE 30th International Conference on Advanced Information Networking and Applications (AINA), Crans-Montana, Switzerland.10.1109/AINA.2016.158 ↗
6. Healthcare and Anomaly Detection: Using Machine Learning to Predict Anomalies in Heart Rate Data10.1007/s00146-020-00985-1 ↗
7. Sensor Anomaly Detection in Wireless Sensor Networks for Healthcare10.3390/s150408764 ↗
8. Pereira, J., and Silveira, M. (March, January 27). Learning Representations from Healthcare Time Series Data for Unsupervised Anomaly Detection. Proceedings of the 2019 IEEE International Conference on Big Data and Smart Computing (BigComp), Kyoto, Japan.10.1109/BIGCOMP.2019.8679157 ↗
9. Kavitha, M., Srinivas, P.V.V.S., Kalyampudi, P.S.L., Choragudi, S.F., and Srinivasulu, S. (2021, January 2–4). Machine Learning Techniques for Anomaly Detection in Smart Healthcare. Proceedings of the 2021 Third International Conference on Inventive Research in Computing Applications (ICIRCA), Coimbatore, India.10.1109/ICIRCA51532.2021.9544795 ↗
10. Anomaly Detection for Industrial Quality Assurance: A Comparative Evaluation of Unsupervised Deep Learning Models10.1016/j.cie.2023.109045 ↗
11. Stojanovic, L., Dinic, M., Stojanovic, N., and Stojadinovic, A. (2016, January 5–8). Big-Data-Driven Anomaly Detection in Industry (4.0): An Approach and a Case Study. Proceedings of the 2016 IEEE International Conference on Big Data (Big Data), Washington, DC, USA.10.1109/BigData.2016.7840777 ↗
12. Machine Learning-Based Anomaly Detection via Integration of Manufacturing, Inspection and after-Sales Service Data10.1108/IMDS-06-2016-0195 ↗
13. A New Statistical Approach to Automated Quality Control in Manufacturing Processes10.1016/j.jmsy.2015.06.001 ↗
14. An Efficient Hybrid System for Anomaly Detection in Social Networks10.1186/s42400-021-00074-w ↗
15. Identifying Buzz in Social Media: A Hybrid Approach Using Artificial Bee Colony and k-Nearest Neighbors for Outlier Detection10.1007/s13278-017-0461-2 ↗
16. Anomaly Detection in Online Social Networks10.1016/j.socnet.2014.05.002 ↗
17. A Framework for Big Data Analytics in Commercial Social Networks: A Case Study on Sentiment Analysis and Fake Review Detection for Marketing Decision-Making10.1016/j.indmarman.2019.08.003 ↗
18. A Review of Current Machine Learning Approaches for Anomaly Detection in Network Traffic
19. AI-Driven Cybersecurity: An Overview, Security Intelligence Modeling and Research Directions10.1007/s42979-021-00557-0 ↗
20. A Survey of Network Anomaly Detection Techniques10.1016/j.jnca.2015.11.016 ↗
21. Chalapathy, R., and Chawla, S. (2019). Deep Learning for Anomaly Detection: A Survey. arXiv.10.1145/3394486.3406704 ↗
22. Bank, D., Koenigstein, N., and Giryes, R. (2021). Autoencoders. arXiv.
23. Kingma, D.P., and Welling, M. (2022). Auto-Encoding Variational Bayes. arXiv.
24. Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4–9). Attention Is All You Need. Proceedings of the Advances in Neural Information Processing Systems 30 (NIPS 2017), Long Beach, CA, USA.
25. Goodfellow, I.J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., and Bengio, Y. (2014). Generative Adversarial Networks. arXiv.
26. Donahue, J., Krähenbühl, P., and Darrell, T. (2017). Adversarial Feature Learning. arXiv.
27. Staudemeyer, R.C., and Morris, E.R. (2019). Understanding LSTM—A Tutorial into Long Short-Term Memory Recurrent Neural Networks. arXiv.
28. Anomaly VAE-Transformer: A Deep Learning Approach for Anomaly Detection in Decentralized Finance10.1109/ACCESS.2023.3313448 ↗
29. A Survey On: “Log Analysis With Elk Stack Tool”
30. Stoleriu, R., Puncioiu, A., and Bica, I. (2021, January 1–3). Cyber Attacks Detection Using Open Source ELK Stack. Proceedings of the 2021 13th International Conference on Electronics, Computers and Artificial Intelligence (ECAI), Pitesti, Romania.10.1109/ECAI52376.2021.9515120 ↗
31. Sánchez-Zas, C., Larriva-Novo, X., Villagrá, V.A., Rodrigo, M.S., and Moreno, J.I. (2022). Design and Evaluation of Unsupervised Machine Learning Models for Anomaly Detection in Streaming Cybersecurity Logs. Mathematics, 10.10.3390/math10214043 ↗
32. Ferreira, L., Pilastri, A., Martins, C.M., Pires, P.M., and Cortez, P. (2021, January 18–22). A Comparison of AutoML Tools for Machine Learning, Deep Learning and XGBoost. Proceedings of the 2021 International Joint Conference on Neural Networks (IJCNN), Shenzhen, China. Available online: https://ieeexplore.ieee.org/abstract/document/9534091.10.1109/IJCNN52387.2021.9534091 ↗
33. Candel, A., Parmar, V., LeDell, E., and Arora, A. (2016). Deep Learning with H2O, H2O ai Inc.
34. Cui, J., Bai, L., Zhang, X., Lin, Z., and Liu, Q. (2024). The Attention-Based Autoencoder for Network Traffic Classification with Interpretable Feature Representation. Symmetry, 16.10.3390/sym16050589 ↗
35. An Improved Stacked Auto-Encoder for Network Traffic Flow Classification10.1109/MNET.2018.1800078 ↗
36. Song, Y., Hyun, S., and Cheong, Y.-G. (2021). Analysis of Autoencoders for Network Intrusion Detection. Sensors, 21.10.3390/s21134294 ↗
37. A Comprehensive Survey on Design and Application of Autoencoder in Deep Learning10.1016/j.asoc.2023.110176 ↗
38. Autoencoders and Their Applications in Machine Learning: A Survey10.1007/s10462-023-10662-6 ↗
39. Anomaly-Based Intrusion Detection From Network Flow Features Using Variational Autoencoder10.1109/ACCESS.2020.3001350 ↗
40. Wei, W., Wu, H., and Ma, H. (2019). An AutoEncoder and LSTM-Based Traffic Flow Prediction Method. Sensors, 19.10.3390/s19132946 ↗
41. Hwang, R.-H., Peng, M.-C., and Huang, C.-W. (2019, January 9–13). Detecting IoT Malicious Traffic Based on Autoencoder and Convolutional Neural Network. Proceedings of the 2019 IEEE Globecom Workshops (GC Wkshps), Waikoloa, HI, USA.10.1109/GCWkshps45667.2019.9024425 ↗
42. Gharib, M., Mohammadi, B., Dastgerdi, S.H., and Sabokrou, M. (2019). AutoIDS: Auto-Encoder Based Method for Intrusion Detection System. arXiv, Available online: https://arxiv.org/abs/1911.03306v1.
43. Xu, H., Chen, W., Zhao, N., Li, Z., Bu, J., Li, Z., Liu, Y., Zhao, Y., Pei, D., and Feng, Y. (2018, January 23–27). Unsupervised Anomaly Detection via Variational Auto-Encoder for Seasonal KPIs in Web Applications. Proceedings of the 2018 World Wide Web Conference, International World Wide Web Conferences Steering Committee: Republic and Canton of Geneva, CHE, Lyon, France.10.1145/3178876.3185996 ↗
44. InSDN: A Novel SDN Intrusion10.1109/ACCESS.2020.3022633 ↗
45. Kim, G.-Y., Lim, S.-M., and Euom, I.-C. (2022). A Study on Performance Metrics for Anomaly Detection Based on Industrial Control System Operation Data. Electronics, 11.10.3390/electronics11081213 ↗
46. Tsimenidis, S. (2020). Limitations of Deep Neural Networks: A Discussion of G. Marcus’ Critical Appraisal of Deep Learning. arXiv.
47. EFS-YOLO: A Lightweight Network Based on Steel Strip Surface Defect Detection10.1088/1361-6501/ad66fe ↗
48. Unsupervised Person Re-Identification Based on Adaptive Information Supplementation and Foreground Enhancement10.1049/ipr2.13277 ↗
49. Howard, A.G., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., and Adam, H. (2017). MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. arXiv.
50. Tiny Machine Learning: Progress and Futures10.1109/MCAS.2023.3302182 ↗
51. Lundberg, S., and Lee, S.-I. (2017). A Unified Approach to Interpreting Model Predictions. arXiv.
52. An Adaptive Global–Local Generalized FEM for Multiscale Advection–Diffusion Problems10.1016/j.cma.2023.116548 ↗
53. Ensemble of Autoencoders for Anomaly Detection in Biomedical Data: A Narrative Review10.1109/ACCESS.2024.3360691 ↗
54. Del Buono, F., Calabrese, F., Baraldi, A., Paganelli, M., and Guerra, F. (2022). Novelty Detection with Autoencoders for System Health Monitoring in Industrial Environments. Appl. Sci., 12.10.3390/app12104931 ↗
55. Anomaly Detection in Medical Imaging With Deep Perceptual Autoencoders10.1109/ACCESS.2021.3107163 ↗
56. Unsupervised Deep Anomaly Detection for Medical Images Using an Improved Adversarial Autoencoder10.1007/s10278-021-00558-8 ↗
57. Yao, R., Liu, C., Zhang, L., and Peng, P. (2019, January 17–20). Unsupervised Anomaly Detection Using Variational Auto-Encoder Based Feature Extraction. Proceedings of the 2019 IEEE International Conference on Prognostics and Health Management (ICPHM), San Francisco, CA, USA.10.1109/ICPHM.2019.8819434 ↗
58. Schreyer, M., Sattarov, T., Borth, D., Dengel, A., and Reimer, B. (2017). Detection of Anomalies in Large Scale Accounting Data Using Deep Autoencoder Networks. arXiv, Available online: https://arxiv.org/abs/1709.05254v2.
59. Wong, L., Liu, D., Berti-Equille, L., Alnegheimish, S., and Veeramachaneni, K. (2022, January 17–20). AER: Auto-Encoder with Regression for Time Series Anomaly Detection. Proceedings of the 2022 IEEE International Conference on Big Data (Big Data), Osaka, Japan.10.1109/BigData55660.2022.10020857 ↗
60. A Deep Convolutional Autoencoder-Based Approach for Anomaly Detection With Industrial, Non-Images, 2-Dimensional Data: A Semiconductor Manufacturing Case Study10.1109/TASE.2022.3141186 ↗
61. Real Time Detection of Acoustic Anomalies in Industrial Processes Using Sequential Autoencoders10.1111/exsy.12564 ↗
62. Givnan, S., Chalmers, C., Fergus, P., Ortega-Martorell, S., and Whalley, T. (2022). Anomaly Detection Using Autoencoder Reconstruction upon Industrial Motors. Sensors, 22.10.3390/s22093166 ↗
63. MEFP-Net: A Dual-Encoding Multi-Scale Edge Feature Perception Network for Skin Lesion Segmentation10.1109/ACCESS.2024.3467678 ↗