Related Experiment Video
Updated: Jun 6, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
Published on: December 15, 2023
Embedding Tree-Based Intrusion Detection System in Smart Thermostats for Enhanced IoT Security.
Abbas Javed1, Muhammad Naeem Awais1, Ayyaz-Ul-Haq Qureshi2
1Department of Electrical and Computer Engineering, COMSATS University Islamabad, Lahore Campus, Lahore 54000, Pakistan.
Resource-constrained IoT devices can be secured with embedded intrusion detection systems (IDS). A novel dataset and tree-based IDS achieved high accuracy in detecting denial of service (DoS) and man-in-the-middle (MITM) attacks on smart thermostats.
Area of Science:
- Cybersecurity
- Internet of Things (IoT)
- Embedded Systems
Background:
- IoT devices with limited resources are vulnerable to attacks like Denial of Service (DoS) and Man-in-the-Middle (MITM), especially without gateways.
- Traditional Intrusion Detection Systems (IDS) are often deployed at the edge or cloud, but require on-device deployment for gateway-less IoT environments.
- Existing datasets lack features from microcontroller-based IoT devices, hindering the development of effective embedded IDS.
Purpose of the Study:
- To develop a unique dataset (Intrusion Detection in the Smart Homes - IDSH) with features retrievable from microcontroller-based IoT devices.
- To embed a Tree-based IDS within a smart thermostat for real-time intrusion detection.
- To evaluate the performance of the embedded IDS in detecting common IoT attacks without external infrastructure.
Main Methods:
- Creation of the Intrusion Detection in the Smart Homes (IDSH) dataset using microcontroller-based IoT device features.
- Implementation of a Tree-based Intrusion Detection System (IDS) directly onto a smart thermostat.
- Real-time testing and performance evaluation of the embedded IDS against DoS and MITM attacks.
Main Results:
- The embedded Tree-based IDS achieved 98.71% accuracy for binary classification and 97.51% for multi-classification.
- The system demonstrated a fast inference time, with 276 microseconds for binary and 273 microseconds for multi-classification.
- Real-time tests confirmed the smart thermostat's capability to detect DoS and MITM attacks autonomously.
Conclusions:
- Embedded IDS on resource-constrained IoT devices are feasible and effective for real-time threat detection.
- The developed IDSH dataset provides valuable features for training IDS on microcontroller-level IoT devices.
- This approach enhances IoT security by enabling on-device attack detection without reliance on gateways or cloud infrastructure.
Related Concept Videos
Survival Tree
Building a Survival Tree
Constructing a...
Defenses Against Pathogens and Herbivores
Assessing Body Temperature - Axilla
Step 1: Perform hand hygiene and put on clean gloves to maintain infection control and prevent cross-contamination.
Step 2: Prepare the patient by explaining the procedure to ensure understanding and cooperation. Ensure privacy, expose the axilla, and inform the patient that minimal movement is crucial for an accurate reading.
Step 3: Adjust the patient’s clothing to expose only the axilla. It minimizes...
Assessing Body Temperature - Temporal Artery
Step 1: Perform hand hygiene and don a fresh pair of gloves to prevent cross-infection and ensure patient safety.
Step 2: Explain the procedure to the patient to establish trust. Clear communication establishes trust with the patient, ensures they understand what to expect, promotes cooperation, and enhances comfort during the procedure.
Step 3: Assess the patient's...

