DeepSynth: A Robust Multi-Layer Neural Detection of Coordinated Latent Anomalies in High-Dimensional Identity Systems
Keywords:
Coordinated anomaly detection, Deep neural networks, Ensemble robustness, High-dimensional data, Identity systems, Latent representation learningAbstract
The proliferation of high-dimensional, multi-modal behavioral signals in modern digital identity ecosystems has been accompanied by the evolution of adversarial strategies from isolated point anomalies to coordinated deviations across correlated feature subspaces. Existing anomaly detection frameworks primarily model marginal feature deviations, which limits their sensitivity to the higher-order dependency structures that characterize coordinated attacks. This research introduces DeepSynth, a coordination-aware multi-layer neural framework to detect synchronized latent anomalies in complex identity ecosystems. The framework integrates hierarchical representation learning with covariance-informed latent modeling to explicitly capture inter-feature dependencies. Anomaly scoring integrates reconstruction residuals, Euclidean latent deviation, Mahalanobis distance, and a normalized covariance-based coordination metric to quantify coordinated deviations across latent features. A latent-level ensemble aggregation coupled with theoretical variance-reduction enhances robustness against noise, imbalance, and adversarial variability. Empirical evaluation on heterogeneous identity datasets comprising behavioral logs, transactional records, and synthetic attack simulations demonstrates the efficacy of the framework. DeepSynth achieves a peak detection accuracy of 93.8% and an AUC-ROC of 95.1%, significantly outperforming strong baselines including Deep SVDD, Isolation Forest, and LSTM encoder-decoders ($p < 0.01$, paired bootstrap test). Furthermore, component-wise analysis confirms that explicit latent coordination modeling provides measurable gains beyond reconstruction-only objectives. These findings establish that resolving higher-order latent dependency structures is critical for robust anomaly detection in high-dimensional identity ecosystems. Future work includes deriving theoretical generalization bounds for coordination-aware anomaly detection under evolving covariance structures
Downloads
References
Y. Ye, T. Li, D. Adjeroh, and S. S. Iyengar, “A survey on malware detection using data mining techniques,” ACM Comput. Surv., vol. 50, no. 3, May 2018, doi: 10.1145/3073559.
M. Kang, “Machine Learning: Anomaly Detection,” in Prognostics and Health Management of Electronics: Fundamentals, Machine Learning, and the Internet of Things. Wiley, 2018, pp. 131–162, doi: 10.1002/9781119515326.ch6.
A. Basharat, A. Gritai, and M. Shah, “Learning object motion patterns for anomaly detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), 2008.
S. Kumar, S. Prasanna, and X. Ruan, “A unified hybrid machine learning architecture for robust identity anomaly detection in large-scale digital ecosystems,” J. Electr. Syst., vol. 14, no. 1, pp. 160–173, 2018.
N. Papernot et al., “Scalable private learning with PATE,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2018.
X. Zhu and Y. Badr, “Identity management systems for the internet of things: A survey towards blockchain solutions,” Sensors, vol. 18, no. 12, 2018, doi: 10.3390/s18124215.
N. Papernot et al., “Scalable private learning with PATE,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2018.
M. Iturbe, I. Garitano, U. Zurutuza, and R. Uribeetxeberria, “Towards large-scale, heterogeneous anomaly detection systems in industrial networks: A survey of current trends,” Hindawi, 2017, doi: 10.1155/2017/9150965.
W. G. Hatcher and W. Yu, “A survey of deep learning: Platforms, applications and emerging research trends,” IEEE Access, vol. 6, pp. 24411–24432, 2018, doi: 10.1109/ACCESS.2018.2830661.
N. Souly, C. Spampinato, and M. Shah, “Semi-supervised semantic segmentation using generative adversarial network,” in Proc. IEEE Int. Conf. Comput. Vis. (ICCV), 2017, pp. 5689–5697, doi: 10.1109/ICCV.2017.606.
Y. Ikeda, K. Tajiri, Y. Nakano, K. Watanabe, and K. Ishibashi, “Estimation of dimensions contributing to detected anomalies with variational autoencoders,” Nov. 2018. [Online]. Available: https://arxiv.org/pdf/1811.04576
H. Zenati, M. Romain, C. S. Foo, B. Lecouat, and V. Chandrasekhar, “Adversarially learned anomaly detection,” in Proc. IEEE Int. Conf. Data Mining (ICDM), 2018, pp. 727–736, doi: 10.1109/ICDM.2018.00088.
S. K. Lim, Y. Loo, N. T. Tran, N. M. Cheung, G. Roig, and Y. Elovici, “DOPING: Generative data augmentation for unsupervised anomaly detection with GAN,” in Proc. IEEE Int. Conf. Data Mining (ICDM), 2018, pp. 1122–1127, doi: 10.1109/ICDM.2018.00146.
Y. Thu, K. Takabuchi, K. Fukai, and N. Iwahashi, “Robot language acquisition based on sequence-to-sequence learning,” 2017. [Online]. Available: https://meral.edu.mm/record/5000/files/proceeding_total-pages-461-472.pdf
J. Ker, L. Wang, J. Rao, and T. Lim, “Deep learning applications in medical image analysis,” IEEE Access, vol. 6, pp. 9375–9379, 2017, doi: 10.1109/ACCESS.2017.2788044.
L. Ruff et al., “Deep one-class classification,” in Proc. Int. Conf. Mach. Learn. (ICML), 2018. [Online]. Available: https://proceedings.mlr.press/v80/ruff18a.html
B. Zong et al., “Deep autoencoding Gaussian mixture model for unsupervised anomaly detection,” in Proc. Int. Conf. Learn. Represent. (ICLR), 2018. [Online]. Available: https://openreview.net/forum?id=BJJLHbb0-
N. Chawla and W. Wang, “Front matter,” in Proc. SIAM Int. Conf. Data Mining, 2017, pp. 1–10, doi: 10.1137/1.9781611974973. fm.
Z. I. Skordilis et al., “Multichannel speech enhancement using MEMS microphones,” in Proc. IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP), 2015, pp. 2729–2733, doi: 10.1109/ICASSP.2015.7178467.
S. Byon et al., “Network connectivity of IPTV STB low power mode,” in Proc. Int. Conf. Platform Technol. Service (PlatCon), 2016, doi: 10.1109/PlatCon.2016.7456809.
S. M. Erfani, S. Rajasegarar, S. Karunasekera, and C. Leckie, “High-dimensional and large-scale anomaly detection using a linear one-class SVM with deep learning,” Pattern Recognit., vol. 58, pp. 121–134, 2016, doi: 10.1016/j.patcog.2016.03.028.
P. Malhotra et al., “LSTM-based encoder-decoder for multi-sensor anomaly detection,” Jul. 2016.
B. R. Kiran, D. M. Thomas, and R. Parakkal, “An overview of deep learning based methods for unsupervised and semi-supervised anomaly detection in videos,” 2018, doi: 10.3390/jimaging4020036.
D. Xu, E. Ricci, Y. Yan, J. Song, and N. Sebe, “Learning deep representations of appearance and motion for anomalous event detection,” in BMVC, 2015, pp. 8.1–8.12, doi: 10.5244/c.29.8.
C. Shen, Y. Qi, J. Wang, G. Cai, and Z. Zhu, “An automatic and robust feature learning method for rotating machinery fault diagnosis based on contractive autoencoder,” Eng. Appl. Artif. Intell., vol. 76, pp. 170–184, 2018, doi: 10.1016/j.engappai.2018.09.010.
S. Rayana and L. Akoglu, “Less is more: Building selective anomaly ensembles,” ACM Trans. Knowl. Discov. Data, vol. 10, no. 4, May 2016, doi: 10.1145/2890508.
A. Singh, “Anomaly detection for temporal data using long short-term memory (LSTM),” 2017. [Online]. Available: https://www.diva-portal.org/smash/record.jsf?pid=diva2:1149130
Y. Guo et al., “Multidimensional time series anomaly detection: A GRU-based Gaussian mixture variational autoencoder approach,” in Proc. Mach. Learn. Res., 2018, pp. 97–112. [Online]. Available: http://proceedings.mlr.press/v95/guo18a.html
Q. Leng, H. Qi, J. Miao, W. Zhu, and G. Su, “One-class classification with extreme learning machine,” Math. Probl. Eng., vol. 2015, 2015, doi: 10.1155/2015/412957.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
