Journal Article2025Cited by 4

Memristor-Based Neuromorphic System for Unsupervised Online Learning and Network Anomaly Detection on Edge Devices

Md Shahanur Alam, Chris Yakopcic, Raqibul Hasan, Tarek M. Taha

Information

MDPI AG, Vol. 16, Issue 3, pp. 222, ISBN: 2078-2489

DOI: 10.3390/info16030222Open AccessURL

Abstract

An ultra-low-power, high-performance online learning and anomaly detection system has been developed for edge security applications. Designed to support personalized learning without relying on cloud data processing, the system employs sample-wise learning, eliminating the need for storing entire datasets for training. Built using memristor-based analog neuromorphic and in-memory computing techniques, the system integrates two unsupervised autoencoder neural networks—one utilizing optimized crossbar weights and the other performing real-time learning to detect novel intrusions. Threshold optimization and anomaly detection are achieved through a fully analog Euclidean Distance (ED) computation circuit, eliminating the need for floating-point processing units. The system demonstrates 87% anomaly detection accuracy, achieves a performance of 16.1 GOPS—774× faster than the ASUS Tinkerboard edge processor—and delivers an energy efficiency of 783 GOPS/W, consuming only 20.5 mW during anomaly detection.

Keywords

  • memristors
  • neuromorphic computing
  • in-memory computing
  • network anomaly detection
  • edge security
  • Autoencoder
  • intrusion detection
  • personalized learning

CCDS Authors

Raqibul Hasan, PhD
Raqibul Hasan, PhD

Raqibul Hasan, PhD

  • Director, NEST & IPT Wings

  • Assistant Professor

    Department of Computer Science and Engineering

    Independent University, Bangladesh (IUB)

References

  1. 1.Sylvestre-Alvise Rebuffi, Alexander Kolesnikov, Georg Sperl, Christoph H. Lampert. (2017). iCaRL: Incremental Classifier and Representation Learning. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 5533–5542[10.1109/cvpr.2017.587]
  2. 2.Abu Sebastian, Manuel Le Gallo, Riduan Khaddam-Aljameh, Evangelos Eleftheriou. (2020). Memory devices and applications for in-memory computing. Nature Nanotechnology, 15(7), 529–544[10.1038/s41565-020-0655-z]
  3. 3.Mohammed A. Zidan, John Paul Strachan, Wei D. Lu. (2017). The future of electronics based on memristive systems. Nature Electronics, 1(1), 22–29[10.1038/s41928-017-0006-8]
  4. 4.Bruno Bogaz Zarpelão, Rodrigo Sanches Miani, Cláudio Toshio Kawakani, Sean Carlisto de Alvarenga. (2017). A survey of intrusion detection in Internet of Things. Journal of Network and Computer Applications, 84, 25–37[10.1016/j.jnca.2017.02.009]
  5. 5.Jian Wang, Siyuan Lu, Shui-Hua Wang, Yu-Dong Zhang. (2021). A review on extreme learning machine. Multimedia Tools and Applications, 81(29), 41611–41660[10.1007/s11042-021-11007-7]
  6. 6.Raghubir Singh, Sukhpal Singh Gill. (2023). Edge AI: A survey. Internet of Things and Cyber-Physical Systems, 3, 71–92[10.1016/j.iotcps.2023.02.004]
  7. 7.Mingyi Rao, Hao Tang, Jiangbin Wu, Wenhao Song, Max Zhang, Wenbo Yin, Ye Zhuo, Fatemeh Kiani, Benjamin Chen, Xiangqi Jiang, Hefei Liu, Hung-Yu Chen, Rivu Midya, Fan Ye, Hao Jiang, Zhongrui Wang, Mingche Wu, Miao Hu, Han Wang, Qiangfei Xia, Ning Ge, Ju Li, J. Joshua Yang. (2023). Thousands of conductance levels in memristors integrated on CMOS. Nature, 615(7954), 823–829[10.1038/s41586-023-05759-5]
  8. 8.Srikanth Thudumu, Philip Branch, Jiong Jin, Jugdutt Singh. (2020). A comprehensive survey of anomaly detection techniques for high dimensional big data. Journal Of Big Data, 7(1)[10.1186/s40537-020-00320-x]
  9. 9.Shimeng Yu, Yi Wu, H.-S. Philip Wong. (2011). Investigating the switching dynamics and multilevel capability of bipolar metal oxide resistive switching memory. Applied Physics Letters, 98(10)[10.1063/1.3564883]
  10. 10.Abdulrahman Takiddin, Muhammad Ismail, Usman Zafar, Erchin Serpedin. (2022). Deep Autoencoder-Based Anomaly Detection of Electricity Theft Cyberattacks in Smart Grids. IEEE Systems Journal, 16(3), 4106–4117[10.1109/jsyst.2021.3136683]
  11. 11.Mansi Bhavsar, Kaushik Roy, John Kelly, Odeyomi Olusola. (2023). Anomaly-based intrusion detection system for IoT application. Discover Internet of Things, 3(1)[10.1007/s43926-023-00034-5]
  12. 12.Olga Krestinskaya, Khaled Nabil Salama, Alex Pappachen James. (2018). Learning in Memristive Neural Network Architectures Using Analog Backpropagation Circuits. IEEE Transactions on Circuits and Systems I Regular Papers, 66(2), 719–732[10.1109/tcsi.2018.2866510]
  13. 13.Tyler L. Hayes, Christopher Kanan. (2020). Lifelong Machine Learning with Deep Streaming Linear Discriminant Analysis. IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), 887–896[10.1109/cvprw50498.2020.00118]
  14. 14.Syed Shakib Sarwar, Aayush Ankit, Kaushik Roy. (2019). Incremental Learning in Deep Convolutional Neural Networks Using Partial Network Sharing. IEEE Access, 8, 4615–4628[10.1109/access.2019.2963056]
  15. 15.Ashfahani, A., Pratama, M., Lughofer, E., Ong, Y.S.. (2020). DEVDAN: deep evolving denoising autoencoder. UniSA Research Outputs Repository (University of South Australia)[10.1016/j.neucom.2019.07.106]
  16. 16.Chris Yakopcic, Tarek M. Taha, Guru Subramanyam, Robinson E. Pino. (2013). Memristor SPICE model and crossbar simulation based on devices with nanosecond switching time. International Joint Conference on Neural Networks (IJCNN), 1–7[10.1109/ijcnn.2013.6706773]
  17. 17.Ekaterina Govorkova, Ema Puljak, Thea Aarrestad, Thomas James, Vladimir Loncar, Maurizio Pierini, Adrian Alan Pol, Nicolò Ghielmetti, Maksymilian Graczyk, Sioni Summers, Jennifer Ngadiuba, Thong Q. Nguyen, Javier Duarte, Zhenbin Wu. (2022). Autoencoders on field-programmable gate arrays for real-time, unsupervised new physics detection at 40 MHz at the Large Hadron Collider. Nature Machine Intelligence, 4(2), 154–161[10.1038/s42256-022-00441-3]
  18. 18.Yandong Luo, Xiaochen Peng, Shimeng Yu. (2019). MLP+NeuroSimV3.0. International Conference on Neuromorphic Systems (ICONS), 1–7[10.1145/3354265.3354266]
  19. 19.Sina Faezi, Rozhin Yasaei, Anomadarshi Barua, Mohammad Abdullah Al Faruque. (2021). Brain-Inspired Golden Chip Free Hardware Trojan Detection. IEEE Transactions on Information Forensics and Security, 16, 2697–2708[10.1109/tifs.2021.3062989]
  20. 20.Hongwu Jiang, Wantong Li, Shanshi Huang, Stefan Cosemans, Francky Catthoor, Shimeng Yu. (2021). Analog-to-Digital Converter Design Exploration for Compute-in-Memory Accelerators. IEEE Design and Test, 39(2), 48–55[10.1109/mdat.2021.3050715]
  21. 21.Ziyu Lv, Shirui Zhu, Yan Wang, Yanyun Ren, Mingtao Luo, Hanning Wang, Guohua Zhang, Yongbiao Zhai, Shilong Zhao, Ye Zhou, Minghao Jiang, Yan‐Bing Leng, Su‐Ting Han. (2024). Development of Bio‐Voltage Operated Humidity‐Sensory Neurons Comprising Self‐Assembled Peptide Memristors. Advanced Materials, 36(33), e2405145[10.1002/adma.202405145]
  22. 22.Vladyslav Hamolia, Viktor Melnyk, Pavlo Zhezhnych, Anna Shilinh. (2020). INTRUSION DETECTION IN COMPUTER NETWORKS USING LATENT SPACE REPRESENTATION AND MACHINE LEARNING. International Journal of Computing, 442–448[10.47839/ijc.19.3.1893]
  23. 23.V. Sidharth, C. R. Kavitha. (2021). Network Intrusion Detection System Using Stacking and Boosting Ensemble Methods. International Conference on Inventive Research in Computing Applications (ICIRCA), 357–363[10.1109/icirca51532.2021.9545022]
  24. 24.Ziyu Lv, Ming‐Hao Jiang, Hui‐Ying Liu, Qing‐Xiu Li, Tao Xie, Jingya Yang, Yan Wang, Yongbiao Zhai, Guanglong Ding, Shirui Zhu, Jia‐Hua Li, Miao Zhang, Ye Zhou, Bobo Tian, Wai‐Yeung Wong, Su‐Ting Han. (2025). Temperature‐Resilient Polymeric Memristors for Effective Deblurring in Static and Dynamic Imaging. Advanced Functional Materials, 35(23)[10.1002/adfm.202424382]
  25. 25.Musatafa Abbas Abbood Albadr, Sabrina Tiun, Masri Ayob, Fahad Taha Al-Dhief, Taj-Aldeen Naser Abdali, Aymen Fadhil Abbas. (2021). Extreme Learning Machine for Automatic Language Identification Utilizing Emotion Speech Data. International Conference on Electrical, Communication, and Computer Engineering (ICECCE), 1–6[10.1109/icecce52056.2021.9514107]
  26. 26.Raqibul Hasan, Tarek M. Taha, Chris Yakopcic. (2017). On-chip training of memristor based deep neural networks. International Joint Conference on Neural Networks (IJCNN), 3527–3534[10.1109/ijcnn.2017.7966300]
  27. 27.Zhekang Dong, Chun Sing Lai, Zhaowei Zhang, Donglian Qi, Mingyu Gao, Shukai Duan. (2021). Neuromorphic extreme learning machines with bimodal memristive synapses. Neurocomputing, 453, 38–49[10.1016/j.neucom.2021.04.049]
  28. 28.Chris Yakopcic, Tarek M. Taha, David J. Mountain, Thomas Salter, Matthew J. Marinella, Mark McLean. (2019). Memristor Model Optimization Based on Parameter Extraction From Device Characterization Data. IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems, 39(5), 1084–1095[10.1109/tcad.2019.2912946]
  29. 29.Arnav V. Malawade, Nathan D. Costa, Deepan Muthirayan, Pramod P. Khargonekar, Mohammad A. Al Faruque. (2021). Neuroscience-Inspired Algorithms for the Predictive Maintenance of Manufacturing Systems. IEEE Transactions on Industrial Informatics, 17(12), 7980–7990[10.1109/tii.2021.3062030]
  30. 30.Chenze Shao, Yang Feng. (2022). Overcoming Catastrophic Forgetting beyond Continual Learning: Balanced Training for Neural Machine Translation. Proceedings of the conference - Association for Computational Linguistics. Meeting, 2023–2036[10.18653/v1/2022.acl-long.143]
  31. 31.Baoming Wang, Haotian Zheng, Kun Qian, Xiaoan Zhan, Junliang Wang. (2024). Edge computing and AI-driven intelligent traffic monitoring and optimization. Applied and Computational Engineering, 67(1), 41–46[10.54254/2755-2721/67/2024ma0062]
  32. 32.Md. Shahanur Alam, B. Rasitha Fernando, Yassine Jaoudi, Chris Yakopcic, Raqibul Hasan, Tarek M. Taha, Guru Subramanyam. (2019). Memristor Based Autoencoder for Unsupervised Real-Time Network Intrusion and Anomaly Detection. International Conference on Neuromorphic Systems (ICONS), 1–8[10.1145/3354265.3354267]
  33. 33.Jie Zhang, Yanjiao Li, Wendong Xiao. (2020). Adaptive online sequential extreme learning machine for dynamic modeling. Soft Computing, 25(3), 2177–2189[10.1007/s00500-020-05289-6]
  34. 34.Huanghuang Liang, Hong Cheng, Jiacheng Wei, Lu Zhang, Lu Yang, Yang Zhao, Hongliang Guo. (2019). Memristive Neural Networks: A Neuromorphic Paradigm for Extreme Learning Machine. IEEE Transactions on Emerging Topics in Computational Intelligence, 3(1), 15–23[10.1109/tetci.2018.2849721]
  35. 35.Akshi Kumar, Nitin Sachdeva. (2019). Cyberbullying Checker: Online Bully Content Detection Using Hybrid Supervised Learning. Algorithms for intelligent systems, 371–382[10.1007/978-981-15-0633-8_36]
  36. 36.Vladimir Monakhov, Vajira Thambawita, Pål Halvorsen, Michael A. Riegler. (2023). GridHTM: Grid-Based Hierarchical Temporal Memory for Anomaly Detection in Videos. Sensors, 23(4), 2087[10.3390/s23042087]
  37. 37.A. Nag, R.P. Paily. (2009). Low power squaring and square root circuits using subthreshold MOS transistors. International Conference on Emerging Trends in Electronic and Photonic Devices & Systems (ELECTRO), 96–99[10.1109/electro.2009.5441165]
  38. 38.Suleiman, Mohammed, Issac, Biju. (2018). Performance Comparison of Intrusion Detection \nMachine Learning Classifiers on Benchmark and \nNew Datasets. Northumbria Research Link (Northumbria University)[link]
  39. 39.C. Birk Jones, Cedric Carter, Zachary Thomas. (2018). Intrusion Detection & Response using an Unsupervised Artificial Neural Network on a Single Board Computer for Building Control Resilience. Resilience Week (RWS), 31–37[10.1109/rweek.2018.8473533]
  40. 40.Xiaoping Wang, Shanshan Tu, Wei Zhao, Chengjie Shi. (2021). A novel energy-based online sequential extreme learning machine to detect anomalies over real-time data streams. Neural Computing and Applications, 34(2), 823–831[10.1007/s00521-021-05731-2]
  41. 41.Olga I. Bureneva, M. S. Prasad, Shivani Verma. (2023). FPGA-based Hardware Implementation of the ART-1 classifier. IEEE International Conference on Soft Computing and Measurements (SCM), 171–174[10.1109/scm58628.2023.10159040]
  42. 42.Md Shahanur Alam, Chris Yakopcic, Guru Subramanyam, Tarek M. Taha. (2020). Memristor Based Neuromorphic Adaptive Resonance Theory for One-Shot Online Learning and Network Intrusion Detection. International Conference on Neuromorphic Systems (ICONS), 1–8[10.1145/3407197.3407608]
  43. 43.Hsinyu Tsai, Stefano Ambrogio, Pritish Narayanan, Robert M. Shelby, Charles Mackin, Geoffrey W. Burr. (2019). Analog memory-based techniques for accelerating the training of fully-connected deep neural networks (Conference Presentation). SPIE Novel Patterning Technologies, 29[10.1117/12.2515630]

Cited By

  1. 1.Mostafa Shooshtari, Teresa Serrano‐Gotarredona, Bernabé Linares‐Barranco. (2025). Review of Memristors for In‐Memory Computing and Spiking Neural Networks. Advanced Intelligent Systems, 8(3)[10.1002/aisy.202500806]
  2. 2.Ungbin Byun, Hyesung Na, Sungjun Kim. (2025). Universal Neuromorphic Element: NbOx Memristor with Co‐Existing Volatile, Non‐Volatile, and Threshold Switching. Advanced Functional Materials, 36(15)[10.1002/adfm.202519431]
  3. 3.Haythem Hayouni, Farah Jbali. (2025). Lightweight Neuromorphic‐Temporal Graph Framework for Proactive Defense Against Evolving Cyber Attacks. Security and Privacy, 9(1)[10.1002/spy2.70163]
  4. 4.Wei Li, Yuanguo Wang, Jiazhu Li, Zhihui Han, Yan Chen, Jian Chen. (2025). An Online Learning Framework for Fault Diagnosis of Rolling Bearings Under Distribution Shifts. Mathematics, 13(23), 3763[10.3390/math13233763]
← All publications