Zijie Huang
Abstract
Many anomaly detection techniques have been adopted by Industrial Internet of Things (IIoT) for improving self-diagnosing efficiency and infrastructures security. However, they are usually associated with the issues of computational-hungry and “black box.” Thus, it becomes important to ensure that the detection is not only accurate but also energy-efficient and trustworthy. In this article, we propose an Energy-efficient And Trustworthy Unsupervised anomaly detection framework (EATU) for IIoT. The framework consists of two levels of feature extraction: (1) Autoencoder-based feature extraction and (2) Efficient DeepExplainer-based explainable feature selection. We propose an Efficient DeepExplainer model based on perturbation-focused sampling, which demonstrates the most computational efficiency among state-of-the-art explainable models. With the important features selected by Efficient DeepExplainer, the rationale of why an anomaly detection decision was made is given, enhancing the trustworthiness of the detection as well as improving the accuracy of anomaly detection. Three real-world IIoT datasets with high-dimensional features are used to validate the effectiveness of the proposed framework. Extensive experimental results demonstrate that in comparison with the state-of-the-art, our framework has the attributes of improved accuracy, trustworthiness (in terms of correctness and stability of the explanation), and energy-efficiency (in terms of wall-clock-time and resource usage).
- [1] . 2018. On the robustness of interpretability methods. arXiv preprint arXiv:1806.08049 (2018).Google Scholar
- [2] . 2018. Towards robust interpretability with self-explaining neural networks. In Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS’18). Curran Associates Inc., Red Hook, NY, 7786–7795.Google ScholarDigital Library
- [3] . 2019. Explaining anomalies detected by autoencoders using SHAP. arXiv preprint arXiv:1903.02407 (2019).Google Scholar
- [4] . 2020. Detecting Anomalies in Wafer Manufacturing. Retrieved from https://www.kaggle.com/arbazkhan971/ anomaly-detection.Google Scholar
- [5] . 2018. The industrial internet of things (IIoT): An analysis framework. Comput. Industr. 101 (2018), 1–12.
DOI: DOI: Google ScholarCross Ref
- [6] . 2013. Auto-encoding variational Bayes. arXiv preprint arXiv:1312.6114 (2013).Google Scholar
- [7] . 2014. PCA feature extraction for change detection in multidimensional unlabeled data. IEEE Trans. Neural Netw. Learn. Syst. 25, 1 (2014), 69–80.
DOI: DOI: Google ScholarCross Ref - [8] . 2021. Variational few-shot learning for microservice-oriented intrusion detection in distributed industrial IoT. IEEE Trans. Industr. Inform. (2021), 1–1.
DOI: DOI: Google ScholarCross Ref - [9] . 2017. Mosquitto: Server and client implementation of the MQTT protocol. J. Open Source Softw. 2, 13 (2017), 265.Google ScholarCross Ref
- [10] . 2017. A unified approach to interpreting model predictions. Adv. Neural inf. Process. Syst. 30 (2017).Google Scholar
- [11] . 2021. Green energy efficient routing with deep learning based anomaly detection for internet of things (IoT) communications. Mathematics 9, 5 (2021), 500.Google ScholarCross Ref
- [12] . 2008. SECOM Data Set. Retrieved from http://archive.ics.uci.edu/ml/datasets/ secom.Google Scholar
- [13] . 2018. Understanding AUC-ROC curve. Towards Data Sci. 26 (2018), 220–227.Google Scholar
- [14] 2019. GEE: A gradient-based explainable variational autoencoder for network anomaly detection. In Proceedings of the IEEE Conference on Communications and Network Security (CNS). 91–99.
DOI: DOI: Google ScholarCross Ref - [15] . 2008. Energy minimization with loop fusion and multi-functional-unit scheduling for multidimensional DSP. J. Parallel Distrib. Comput. 68, 4 (2008), 443–455.
DOI: DOI: Google ScholarDigital Library - [16] . 2016. “Why should I trust you?” Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. 1135–1144.Google ScholarDigital Library
- [17] . 2018. Anchors: High-precision model-agnostic explanations. In Proceedings of the AAAI Conference on Artificial Intelligence.Google ScholarCross Ref
- [18] . Hacking Attack Woke up Dallas with Emergency Sirens, Officials Say. Retrieved from https://www.nytimes.com/2017/04/08/us/dallas-emergency-sirens-hacking.html.Google Scholar
- [19] . 2001. Fuzzy K-means clustering with missing values. In Proceedings of the AMIA Symposium. American Medical Informatics Association, 588.Google Scholar
- [20] . 2021. A federated learning approach to anomaly detection in smart buildings. ACM Trans. Internet Things 2, 4 (2021), 1–23.Google ScholarDigital Library
- [21] . 2020. VAE-LIME: deep generative model based approach for local data-driven model interpretability applied to the ironmaking industry. arXiv preprint arXiv:2007.10256 (2020).Google Scholar
- [22] 2020. THE 17 GOALS | Sustainable Development. Retrieved from https://sdgs.un.org/goals.Google Scholar
- [23] . 2012. Pearson’s correlation coefficient. Bmj 345 (2012).Google Scholar
- [24] . 2006. Security protection and checking for embedded system integration against buffer overflow attacks via hardware/software. IEEE Trans. Comput. 55, 4 (2006), 443–453.
DOI: DOI: Google ScholarCross Ref - [25] . 2016. Not just a black box: Learning important features through propagating activation differences. arXiv preprint arXiv:1605.01713 (2016).Google Scholar
- [26] . 2021. Reliable post hoc explanations: Modeling uncertainty in explainability. Adv. Neural Inf. Process. Syst. 34 (2021).Google Scholar
- [27] . 2017. APS Failure at Scania Trucks Data Set. Retrieved from https://archive.ics.uci. edu/ml/datasets/APS+Failure+at+Scania+Trucks##.Google Scholar
- [28] . 2021. A scalable and energy-efficient anomaly detection scheme in wireless SDN-based mMTC networks for IoT. IEEE Internet Things J. 8, 3 (2021), 1388–1405.
DOI: DOI: Google ScholarCross Ref - [29] . 2019. A tensor computation and optimization model for cyber-physical-social big data. IEEE Trans. Sustain. Comput. 4, 4 (2019), 326–339.
DOI: DOI: Google ScholarCross Ref - [30] . 2022. A tensor-based computing and optimization model for intelligent edge services. IEEE Netw. 36, 1 (2022), 40–44.
DOI: DOI: Google ScholarCross Ref - [31] . 2021. Graph neural networks for anomaly detection in industrial internet of things. IEEE Internet Things J. (2021), 1–1.
DOI: DOI: Google ScholarCross Ref - [32] . 2022. A survey of intelligent network slicing management for industrial IoT: Integrated approaches for smart transportation, smart energy, and smart factory. IEEE Commun. Surv. Tutor. 24, 2 (2022), 1175–1211.
DOI: DOI: Google ScholarCross Ref - [33] . 2019. A survey on IIoT security. In Proceedings of the IEEE VTS Asia Pacific Wireless Communications Symposium (APWCS). 1–5.
DOI: DOI: Google ScholarCross Ref - [34] . 2015. Estimating the uncertainty of average F1 scores. In Proceedings of the International Conference on The Theory of Information Retrieval. 317–320.Google ScholarDigital Library
- [35] . 2018. Anomaly detection methods for IIoT networks. In Proceedings of the IEEE International Conference on Service Operations and Logistics, and Informatics (SOLI). 214–219.
DOI: DOI: Google ScholarDigital Library - [36] . 2021. Hierarchical adversarial attacks against graph neural network based IoT network intrusion detection system. IEEE Internet Things J. (2021), 1–1.
DOI: DOI: Google ScholarCross Ref - [37] . 2021. Deep-learning-enhanced multitarget detection for end–edge–cloud surveillance in smart IoT. IEEE Internet Things J. 8, 16 (2021), 12588–12596.
DOI: DOI: Google ScholarCross Ref - [38] . 2021. Energy efficient smart routing based on link correlation mining for wireless edge computing in IoT. IEEE Internet Things J. (2021), 1–1.
DOI: DOI: Google ScholarCross Ref - [39] . 2020. An intelligent anomaly detection scheme for micro-services architectures with temporal and spatial data analysis. IEEE Trans. Cog. Commun. Netw. 6, 2 (2020), 548–561.
DOI: DOI: Google ScholarCross Ref
Index Terms
- An Energy-efficient And Trustworthy Unsupervised Anomaly Detection Framework (EATU) for IIoT
Recommendations
Explainable Anomaly Detection System for Categorical Sensor Data in Internet of Things
Machine Learning and Knowledge Discovery in DatabasesAbstractInternet of things (IoT) applications deploy massive number of sensors to monitor the system and environment. Anomaly detection on streaming sensor data is an important task for IoT maintenance and operation. However, there are two major ...
A Novel Anomaly Detection Method for Worms
DCABES '14: Proceedings of the 2014 13th International Symposium on Distributed Computing and Applications to Business, Engineering and ScienceThis paper proposes a novel anomaly detection method of network worms. The algorithm detects unknown worms by multidimensional worm abnormal detection technology, extracts its feature string via analyzing worm data with leap-style and creates new rules ...
Explainable contextual anomaly detection using quantile regression forests
AbstractTraditional anomaly detection methods aim to identify objects that deviate from most other objects by treating all features equally. In contrast, contextual anomaly detection methods aim to detect objects that deviate from other objects within a ...
Comments