학술논문

GENI: GANs Evaluation of iNjection attacks on IoT
Document Type
Conference
Source
2024 IEEE 10th World Forum on Internet of Things (WF-IoT) Internet of Things (WF-IoT), 2024 IEEE 10th World Forum on. :1-6 Nov, 2024
Subject
Aerospace
Communication, Networking and Broadcast Technologies
Components, Circuits, Devices and Systems
Computing and Processing
Engineering Profession
Fields, Waves and Electromagnetics
General Topics for Engineers
Power, Energy and Industry Applications
Robotics and Control Systems
Signal Processing and Analysis
Transportation
Supervised learning
Detectors
SQL injection
Generative adversarial networks
Pollution measurement
Internet of Things
Security
Reliability
Smart devices
Contamination
IoT security
Generative Adversarial Networks
Anomaly detection
SQL injection attacks
Language
ISSN
2768-1734
Abstract
Internet of Things (IoT) networks, with their extensive connectivity, are particularly vulnerable to cyber threats like injection attacks due to often insufficient security measures on smart devices. Early detection of these attacks is crucial for maintaining the security and reliability of IoT systems. In this research, we tackle the challenge of detecting SQL injection attacks and propose GENI, GANs evaluation of injection attacks on IoT networks. GENI leverages an unsupervised generative adversarial network (GAN) based approach to identify anomalies. We rigorously evaluate GENI’s performance by contrasting two different feature engineering techniques and utilizing a publicly available dataset. Additionally, we conduct a comparative analysis of GENI’s performance against various supervised learning techniques. Our results reveal that GENI exhibits remarkable potential as an anomaly detector for SQL injection attacks, achieving an F1-score of $\mathbf{0. 9 9}$ for normal and $\mathbf{0. 8 9}$ for attack activities at $\mathbf{1 0 \%}$ contamination rate.