Online and Robust Anomaly Detection using Recurrent Neural Network

Document Type : Computer Article

Authors

1 computer and information technology,,

2 Department of Computer engineering, Iran University of Science and Technology

3 Department of Computer engineering, Iran University of Science and Technology, Tehran, Iran

Abstract

In many real-world applications, data is dynamic and noisy. In such a situation, anomaly detection should be performed with an online and robust model against noise. In recent years, recurrent neural networks have been used on data sequences and have achieved good performance in this field. The existing methods do not have sufficient robustness against noise. This paper presents a method for anomaly detection in dynamic graph data using recurrent neural networks that are robust against noise and have sufficient adaptivity to changes in the data pattern. The proposed robust recurrent neural network extracts and introduces anomalies for the purpose of noise management. At the same time, it learns the original patterns in an online manner and is adapted to the changes. To evaluate the proposed method, some experiments are presented that measure its ability in anomaly detection in addition to the learning and adaptation ability in comparison with the existing methods. The results have confirmed the superiority of the proposed method.

Keywords

Main Subjects


[1] V. Chandola, A. Banerjee, and V. Kumar, “Anomaly detection: a survey,” ACM Computing Surveys, Vol. 41, No. 3, 2009, pp. 1–58.
[2] L. T. Thanh, N. V. Dung, N. L. Trung, and K. Abed-Meraim, “Robust Subspace Tracking with Missing Data and Outliers: Novel Algorithm with Convergence Guarantee,” IEEE Transactions on Signal Processing, Vol. 69, 2021, pp. 2070–2085.
[3] Y. Chi, Y. C. Eldar, and R. Calderbank, “PETRELS: Parallel subspace estimation and tracking by recursive least squares from partial observations,” IEEE Transactions on Signal Processing, Vol. 61, No. 23, 2013, pp. 5947–5959.
[4] J. He, L. Balzano, and A. Szlam, “Incremental gradient on the Grassmannian for online foreground and background separation in subsampled video,” in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2012, pp. 1568–1575.
[5] P. Narayanamurthy and N. Vaswani, “Provable dynamic robust PCA or robust subspace tracking,” IEEE Transactions on Information Theory, Vol. 65, No. 3, Mar. 2019, pp. 1547–1577.
[6] A. Sobral, S. Javed, S. K. Jung, T. Bouwmans, and E. H. Zahzah, “Online Stochastic Tensor Decomposition for Background Subtraction in Multispectral Video Sequences,” in Proceedings of the IEEE International Conference on Computer Vision, 2015, pp. 946–953.
[7] M. Amoozegar, B. Minaei-Bidgoli, H. Fanee, and M. Rezghi, “A Drift-Aware Online Learner for Anomaly Detection from Streaming Data,” Computational Intelligence in Electrical Engineering, 2021.
[8] M. Mardani, G. Mateos, and G. B. Giannakis, “Subspace learning and imputation for streaming big data matrices and tensors,” IEEE Transactions on Signal Processing, Vol. 63, No. 10, 2015, pp. 2663–2677.
[9] H. Kasai, “Fast online low-rank tensor subspace tracking by CP decomposition using recursive least squares from incomplete observations,” Neurocomputing, Vol. 347, 2019, pp. 177–190.
[10] Z. Li, Y. Wang, Q. Zhao, S. Zhang, and D. Meng, “A Tensor-Based Online RPCA Model for Compressive Background Subtraction,” IEEE Transactions on Neural Networks and Learning Systems, 2022, pp. 1–15.
[11] M. M. Salut and D. V. Anderson, “Online Tensor Robust Principal Component Analysis,” IEEE Access, Vol. 10, No. May,2022, pp. 69354–69363.
[12] R. Chalapathy and S. Chawla, “Deep Learning for Anomaly Detection: A Survey,” 2019. Accessed: Nov. 20, 2019. [Online]. Available: http://arxiv.org/abs/1901.03407
[13] X. Ma, J. Wu, S. Xue, J. Yang, Q. Z. Sheng, and H. Xiong, “A Comprehensive Survey on Graph Anomaly Detection with Deep Learning,” Vol. 14, No. 8, Jun. 2021, Accessed: Aug. 15, 2021. [Online]. Available: https://arxiv.org/abs/2106.07178v1
[14] G. Pang, C. Shen, L. Cao, and A. Van Den Hengel, “Deep Learning for Anomaly Detection: A Review,” ACM Computing Surveys, Vol. 54, No. 2, 2021.
[15] A. Berroukham, K. Housni, M. Lahraichi, and I. Boulfrifi, “Deep learning-based methods for anomaly detection in video surveillance: a review,” Bulletin of Electrical Engineering and Informatics, Vol. 12, No. 1, 2023, pp. 314–327.
[16] Y. Cui, Z. Liu, and S. Lian, “A Survey on Unsupervised Anomaly Detection Algorithms for Industrial Images,” IEEE Access, Vol. 11, 2023, pp. 55297–55315.
[17] S. Li, X. Yang, H. Zhang, C. Zheng, and Y. Yi, “DSGRAE: Deep Sparse Graph Regularized Autoencoder for Anomaly Detection BT  - Machine Learning for Cyber Security,” Y. Xu, H. Yan, H. Teng, J. Cai, and J. Li, Eds., Cham: Springer Nature Switzerland, 2023, pp. 254–265.
[18] Y. Qi, Y. Wang, X. Zheng, and Z. Wu, “Robust feature learning by stacked autoencoder with maximum correntropy criterion,” in 2014 IEEE international conference on acoustics, speech and signal processing (ICASSP), 2014, pp. 6716–6720.
[19] C. Zhou and R. C. Paffenroth, “Anomaly detection with robust deep autoencoders,” Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, Vol. Part F1296, 2017, pp. 665–674.
[20] Y. Liao, Y. Wang, and Y. Liu, “Graph regularized auto-encoders for image representation,” IEEE Transactions on Image Processing, Vol. 26, No. 6, 2016, pp. 2839–2852.
[21] S. Saurav et al., “Online anomaly detection with concept drift adaptation using recurrent neural networks,” in Proceedings of the ACM India Joint International Conference on Data Science and Management of Data  - CoDS-COMAD ’18, New York, New York, USA: ACM Press, 2018, pp. 78–87.
[22] P. Zhou and J. Feng, “Outlier-robust tensor PCA,” in Proceedings - 30th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2017, 2017, pp. 3938–3946.
[23] L. I. Kuncheva and I. . Žliobait\.e, “On the window size for classification in changing environments,” Intelligent Data Analysis, Vol. 13, No. 6, 2009, pp. 861–872.
[24] W. Feng, N. Guan, Y. Li, X. Zhang, and Z. Luo, “Audio visual speech recognition with multimodal recurrent neural networks,” in 2017 International Joint Conference on neural networks (IJCNN), 2017, pp. 681–688.
[25] N. Vaswani, T. Bouwmans, S. Javed, and P. Narayanamurthy, “Robust subspace learning: Robust PCA, robust subspace tracking, and robust subspace recovery,” IEEE Signal Processing Magazine, Vol. 35, No. 4, 2018, pp. 32–55.
[26] F. Arrigoni, B. Rossi, P. Fragneto, and A. Fusiello, “Robust synchronization in SO (3) and SE (3) via low-rank and sparse matrix decomposition,” Computer Vision and Image Understanding, Vol. 174, 2018, pp. 95–113.
[27] Y. Cui, C. Surpur, S. Ahmad, and J. Hawkins, “A comparative study of HTM and other neural network models for online sequence learning with streaming data,” in 2016 International Joint Conference on Neural Networks (IJCNN), 2016, pp. 1530–1538.
[28] S. Saurav et al., “Online anomaly detection with concept drift adaptation using recurrent neural networks,” in Proceedings of the ACM India Joint International Conference on Data Science and Management of Data - CoDS-COMAD ’18, 2018, pp. 78–87.
[29] M. Mardani, G. Mateos, and G. B. Giannakis, “Dynamic anomalography: Tracking network anomalies via sparsity and low rank,” IEEE Journal on Selected Topics in Signal Processing, Vol. 7, No. 1, 2013, pp. 50–66.
[30] M. Amoozegar, B. Minaei-Bidgoli, M. Rezghi, and H. Fanaee-T, “Extra-adaptive robust online subspace tracker for anomaly detection from streaming networks,” Engineering Applications of Artificial Intelligence, Vol. 94, Sep 2020 p. 103741.
[31] A. Sobral, T. Bouwmans, and E. Zahzah, “Lrslibrary: Low-rank and sparse tools for background modeling and subtraction in videos,” Robust Low-Rank and Sparse Matrix Decomposition: Applications in Image and Video Processing, 2016.