Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

NIDS-Mamba: Lightweight Network Intrusion Detection for IoT Sensor Networks via State Space Models.

Zixiang Ding1, Jiahao Zheng2, Xianyun Wu3

  • 1School of Optoelectronic Engineering, Xidian University, Xi'an 710071, China.

Sensors (Basel, Switzerland)
|May 13, 2026
PubMed
Summary

Related Concept Videos

State Space Representation01:27

State Space Representation

The frequency-domain technique, commonly used in analyzing and designing feedback control systems, is effective for linear, time-invariant systems. However, it falls short when dealing with nonlinear, time-varying, and multiple-input multiple-output systems. The time-domain or state-space approach addresses these limitations by utilizing state variables to construct simultaneous, first-order differential equations, known as state equations, for an nth-order system.
Consider an RLC circuit, a...
State Space to Transfer Function01:21

State Space to Transfer Function

The conversion of state-space representation to a transfer function is a fundamental process in system analysis. It provides a method for transitioning from a time-domain description to a frequency-domain representation, which is crucial for simplifying the analysis and design of control systems.
The transformation process begins with the state-space representation, characterized by the state equation and the output equation. These equations are typically represented as:

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

40 Hz-rTMS modulates spike-LFP coupling and improves cognitive function in 5xFAD mice.

Experimental neurology·2026
Same author

Discovery, Optimization, and Evaluation of Potent and Selective PDGFRβ Inhibitors for the Treatment of Hepatocellular Carcinoma.

Journal of medicinal chemistry·2026
Same author

A field-deployable high-resolution SNP genotyping platform for rapid surveillance of <i>Yersinia pestis</i>.

Virulence·2026
Same author

CBAM meets DropBlock: enhancing robot steering-angle prediction with hybrid attention and structured dropout.

Scientific reports·2026
Same author

Synergizing Strain and Ternary Components in Ultrathin PtCuIr-IrO<sub><i>x</i></sub> Nanodendrites to Enable the C<sub>2</sub> Pathway for Ethanol Electrooxidation.

Inorganic chemistry·2026
Same author

Phase separation of p85β modulates hepatocellular carcinoma progression through POLR1A.

International journal of biological sciences·2026

A new Mamba-based network intrusion detection system (NIDS) effectively secures resource-constrained Internet of Things (IoT) devices. NIDS-Mamba offers high accuracy and efficiency for edge computing, outperforming Transformer models.

Area of Science:

  • Cybersecurity
  • Network Security
  • Edge Computing

Background:

  • Resource-constrained Internet of Things (IoT) nodes necessitate efficient network intrusion detection systems (NIDSs) for edge devices.
  • Existing NIDS solutions often struggle with the limited computing power and memory of IoT devices.

Purpose of the Study:

  • To propose and evaluate a novel NIDS, NIDS-Mamba, optimized for edge deployment on resource-constrained IoT devices.
  • To demonstrate the system's effectiveness in detecting network intrusions while adhering to strict computational and memory limitations.

Main Methods:

  • Developed NIDS-Mamba utilizing Mamba architecture with dynamic sparse attention and a lightweight state space.
  • Validated the model on standardized datasets: NF-UNSW-NB15 and NF-CSE-CIC-IDS2018.
Keywords:
IoTMambaedge computingnetwork intrusion detectionsecurity

Related Experiment Videos

  • Evaluated performance metrics including accuracy, F1-score, AUC, G-Mean, and MCC, alongside throughput and parameter footprint.

    • Main Results:

    • NIDS-Mamba achieved 98.32% accuracy and 0.9996 AUC on NF-CSE-CIC-IDS2018.
    • Demonstrated robustness on NF-UNSW-NB15 with 97.03% G-Mean and 0.9983 AUC, excelling in extreme class imbalance.
    • Achieved an order-of-magnitude improvement in throughput over Transformer baselines with a compact 1.12M parameter design and 5.4MB peak inference memory.

    Conclusions:

    • NIDS-Mamba is highly effective for network intrusion detection on edge IoT devices, particularly in scenarios with extreme class imbalance.
    • The Mamba-based architecture overcomes Transformer limitations, offering a feasible and efficient solution for IoT gateways and sensor nodes.
    • The system's compact design and high performance make it suitable for smart home, industrial IoT, and critical infrastructure security.