PORT SCANNING MALWARE DETECTION IN IOT NETWORKS USING AN AI-BASED IDS FRAMEWORK

The fast growth of the Internet of Things (IoT) has greatly exposed the attack surface, making the IoT networks vulnerable to new malware attacks, especially port scanning malware. These advanced threats have been known to go beyond the standard security solutions like firewalls and signature-based Intrusion Detection Systems (IDS). In this work, an AI-Based IDS framework is proposed, which will utilize Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL) to identify and predict the presence of port scanning malware in IoT networks. The framework is tested with a publicly available set of data on IoT security by both balanced and imbalanced conditions, which guarantees a full performance test. In experiments, it is proven that DL models are more successful than other methods with precision of 98.5, recall of 99.2, F1-score of 98.8 and accuracy of 98.7. The ML traditional models are also very precise and recalls, but the DL models have overall better performance which detects port scanning malware effectively. The results support the potential of the DL-based solutions as the effective measure of boosting the security of IoT in response to the new cyber threats

Authors

Publication Details

Journal
Kufa Journal of Engineering
Published
2026-11-14
DOI
https://doi.org/10.30572/2018/kje/170416
Primary Topic
Network Security and Intrusion Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

PORT SCANNING MALWARE DETECTION IN IOT NETWORKS USING AN AI-BASED IDS FRAMEWORK

Mina Malekzadeh, Mahmood Al-Okashi
Kufa Journal of Engineering
Network Security and Intrusion Detection
article

PORT SCANNING MALWARE DETECTION IN IOT NETWORKS USING AN AI-BASED IDS FRAMEWORK

Mina Malekzadeh, Mahmood Al-Okashi
article en

Abstract

The fast growth of the Internet of Things (IoT) has greatly exposed the attack surface, making the IoT networks vulnerable to new malware attacks, especially port scanning malware. These advanced threats have been known to go beyond the standard security solutions like firewalls and signature-based Intrusion Detection Systems (IDS). In this work, an AI-Based IDS framework is proposed, which will utilize Machine Learning (ML), Deep Learning (DL), and Reinforcement Learning (RL) to identify and predict the presence of port scanning malware in IoT networks. The framework is tested with a publicly available set of data on IoT security by both balanced and imbalanced conditions, which guarantees a full performance test. In experiments, it is proven that DL models are more successful than other methods with precision of 98.5, recall of 99.2, F1-score of 98.8 and accuracy of 98.7. The ML traditional models are also very precise and recalls, but the DL models have overall better performance which detects port scanning malware effectively. The results support the potential of the DL-based solutions as the effective measure of boosting the security of IoT in response to the new cyber threats

Kufa Journal of EngineeringVol. 17(4)
Network Security and Intrusion Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon