Related Experiment Videos
Invariant state modelling for robust adaptive intrusion detection in software-defined internet of things environments
Swathi Gowroju1, S Sai Satyanarayana Reddy2, Shilpa Choudhary3
1Department of CSE (AIML), Sreyas Institute of Engineering and Technology, Hyderabad, Telangana, India.
Scientific Reports
|June 6, 2026
Summary
A new intrusion detection system (IDS), Robust Adaptive Intrusion Detection Using Invariant State (RADIUS), enhances Software-Defined Internet of Things (SD-IoT) security. It achieves high accuracy in detecting complex network attacks.
Area of Science:
- Cybersecurity
- Network Intrusion Detection Systems
- Internet of Things (IoT) Security
Background:
- Software-Defined Internet of Things (SD-IoT) networks face challenges with heterogeneous traffic, limited throughput, and evolving cyber threats.
- Existing intrusion detection systems (IDS) struggle to address the dynamic and complex nature of attacks in SD-IoT environments.
- There is a need for a unified and deployable IDS framework capable of robust and adaptive threat detection.
Purpose of the Study:
- To design and evaluate a novel IDS framework, Robust Adaptive Intrusion Detection Using Invariant State (RADIUS), for SD-IoT networks.
- To address limitations in traffic analysis, detection accuracy, and adaptability to non-stationary attacks.
- To provide interpretable and adaptive threat detection mechanisms.
Main Methods:
- Utilized a Temporal Convolution Encoder (TCE) with dilated and causal convolutions for efficient traffic embedding.
- Incorporated an Adaptive State Transition Module (ASTM) for identifying latent state transitions and enabling adaptive detections.
- Employed dual-objective optimization during training, focusing on prediction accuracy, environment-invariance, and sensitivity to rare events.
- Applied Extreme Value Theory (EVT) with conformal bounds for anomaly scoring and classification calibration.
Main Results:
- The RADIUS framework achieved high performance metrics: 99.8% accuracy, 99.5% precision, 99.8% recall, and 99.7% F1-score.
- Demonstrated consistent performance outperforming the Extended Wrapper Approach (EWA) baseline model.
- Showcased the effectiveness of TCE and ASTM in constructing efficient embeddings and identifying adaptive state transitions.
Conclusions:
- The RADIUS framework offers a robust and deployable solution for intrusion detection in SD-IoT networks.
- Its adaptive capabilities and high accuracy make it suitable for addressing complex and evolving cyber threats.
- RADIUS provides a significant advancement over existing methods, enhancing the security posture of SD-IoT environments.
Related Concept Videos
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...
Consider an RLC circuit, a...
BIBO stability of continuous and discrete -time systems
System stability is a fundamental concept in signal processing, often assessed using convolution. For a system to be considered bounded-input bounded-output (BIBO) stable, any bounded input signal must produce a bounded output signal. A bounded input signal is one where the modulus does not exceed a certain constant at any point in time.
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system.
To determine the BIBO stability, the convolution integral is utilized when a bounded continuous-time input is applied to a Linear Time-Invariant (LTI) system.
Linear time-invariant Systems
A system is linear if it displays the characteristics of homogeneity and additivity, together termed the superposition property. This principle is fundamental in all linear systems. Linear time-invariant (LTI) systems include systems with linear elements and constant parameters.
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be calculated...
The input-output behavior of an LTI system can be fully defined by its response to an impulsive excitation at its input. Once this impulse response is known, the system's reaction to any other input can be calculated...