UDP Flood Attack Detection in IoT Networks Using Decision Tree Algorithm

UDP Flood Denial of Service (DoS) attacks are a critical threat to network security, especially in IoT systems with limited resources. These attacks exploit the UDP (User Datagram Protocol), which does not require a handshake, by flooding the target with high-speed fake packets. As a result, the network experiences bandwidth and resource overload, causing high latency or service crashes. In IoT environments, the impact is more severe because devices typically have low processing capacity and memory. This study focuses on early detection of UDP Flood attacks through network feature analysis and Decision Tree-based classification to mitigate such risks. Testing results show that the model can identify 10 attack samples and 13 normal samples out of 23 test data with 99.98% F1 score. This high accuracy is supported by the dominance of attack packets (99,734) over normal packets (251) in the dataset. The study demonstrates that the combination of UDP port features, packet length, and IP header effectively detects UDP Flood patterns.

• Publication year

  2025

• Venue

  2025 12th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)

• Publication date

  2025-09-25

• Fields of study

  Not labeled

• Identifiers
  DOI 10.1109/EECSI67060.2025.11290186
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• A Machine-Learning-Based Approach for the Detection and Mitigation of Distributed Denial-of-Service Attacks in Internet of Things Environments

  2025cited by this paper
• Cutting-Edge Intrusion Detection in IoT Networks: A Focus on Ensemble Models

  2025cited by this paper
• A Simple Approach for Mitigating a New Flooding Attack in RPL-Based IoT Networks

  2025cited by this paper
• TOCA-IoT: Threshold Optimization and Causal Analysis for IoT Network Anomaly Detection Based on Explainable Random Forest

  2025cited by this paper
• Hybrid Model for Novel Attack Detection Using a Cluster-Based Machine Learning Classification Approach for the Internet of Things (IoT)

  2025cited by this paper
• M-RL: A mobility and impersonation-aware IDS for DDoS UDP flooding attacks in IoT-Fog networks

  2024cited by this paper
• Construction and optimization of vending machine decision support system based on improved C4.5 decision tree

  2024cited by this paper
• Next-generation cyber attack prediction for IoT systems: leveraging multi-class SVM and optimized CHAID decision tree

  2023cited by this paper
• A C4.5 decision tree classifier based floorplanning algorithm for System-on-Chip design

  2022cited by this paper
• Machine Learning for IoT based networks intrusion detection: a comparative study

  2022cited by this paper
• On Modeling Link Flooding Attacks and Defenses

  2021cited by this paper
• DDoS attacks in IoT networks: a comprehensive systematic literature review

  2021cited by this paper
• An Experimental Analysis of Attack Classification Using Machine Learning in IoT Networks

  2021cited by this paper
• Defense against flooding attacks using probabilistic thresholds in the internet of things ecosystem

  2021cited by this paper
• AS-IDS: Anomaly and Signature Based IDS for the Internet of Things

  2021cited by this paper
• ADEPT: Detection and Identification of Correlated Attack Stages in IoT Networks

  2021cited by this paper
• Impact of DoS attack in IoT system and identifying the attacker location for interference attacks

  2021cited by this paper
• Multicast DIS attack mitigation in RPL-based IoT-LLNs

  2021cited by this paper
• Features Selection and Prediction for IoT Attacks

  2021cited by this paper
• Construction of decision tree based on C4.5 algorithm for online voltage stability assessment

  2020cited by this paper
• Machine Learning

  2014cited by this paper

• No citing papers are available for this paper.