GENI: GANs Evaluation of iNjection attacks on IoT

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.