AI and Machine Learning Based Fake Wi-Fi Detection and Alert System.

This paper presented FWDAS, an AI and Machine Learning based Fake Wi-Fi Detection and Alert System designed to protect users from rogue access point attacks in real-world wireless environments. The system integrates RSSI statistics, beacon timing anal-ysis, MAC entropy measurements, and Information Element fingerprinting into a unified feature vector processed by ma-chine learning classifiers. Experimental results confirmed that the Random Forest classifier achieved 98.7% detection accuracy with minimal false positives on a dataset containing 45,000 labeled Wi-Fi scan records. The proposed framework successfully combines anomaly detection, machine learning classification, federated learning, and real-time alert generation into a deployable client-side wireless security solution. Future work includes extending the framework toward Wi-Fi 6E and Wi-Fi 7 networks, improving adversarial robustness, and integrating enterprise Network Access Control platforms.

[1]     S. Xu, Y. Ma, and W. Zhou, ”Man-in-the-Middle Attacks via Rogue Access Points: Mechanisms, Detection, and Mitigation,” IEEE Communications Surveys & Tutorials, vol. 26, no. 1, pp. 412–441, 2024. [2]     Wi-Fi Alliance, ”Wi-Fi Security Landscape Report 2024,” Wi-Fi Alliance Technical Report, 2024. [3]     J. Wright and C. Gribble, ”Detecting Rogue Access Points Using Infrastructure-Side RSSI Correlation,” Proc. IEEE INFOCOM Workshop on Network Security, 2023. [4]     IEEE Std 802.11-2020, ”Wireless LAN Medium Access Control and Physical Layer Specifications,” IEEE, 2020. [5]     M. Vanhoef and F. Piessens, ”Key Reinstallation Attacks: Forcing Nonce Reuse in WPA2,” ACM CCS, 2017. [6]     I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning, MIT Press, 2016. [7]     N. V. Chawla et al., ”SMOTE: Synthetic Minority Over-sampling Technique,” Journal of Artificial Intelligence Research, vol. 16, pp. 321–357, 2002. [8]     B. McMahan et al., ”Communication-Efficient Learning of Deep Networks from Decentralized Data,” AISTATS, 2017. [9]     O. Kus, B. Tavli, and D. Unal, ”Cooperative Rogue Access Point Detection via Distributed Beacon Validation,” IEEE Transactions on Vehicular Technology, vol. 72, no. 4, pp. 5210–5224, 2023. [10]    Z. Liu, X. Chen, and T. Wang, ”DeepWIDS: A Convolutional Neural Network Approach to Rogue Access Point Detection Using Spectral Wi-Fi Features,” IEEE Access, vol. 11, pp. 78341–78356, 2023.