publications

2025

1. Self-supervised radio representation learning: Can we learn multiple tasks?

   Ogechukwu Kanu, Ashkan Eshaghbeigi, and Hatem Abou-Zeid

   In ICC 2025-IEEE International Conference on Communications, 2025

   Abs DOI

   Artificial intelligence (AI) is anticipated to play a pivotal role in 6G. However, a key challenge in developing AI-powered solutions is the extensive data collection and labeling efforts required to train supervised deep learning models. To overcome this, self-supervised learning (SSL) approaches have recently demonstrated remarkable success across various domains by leveraging large volumes of unlabeled data to achieve nearsupervised performance. In this paper, we propose an effective SSL scheme for radio signal representation learning using momentum contrast. By applying contrastive learning, our method extracts robust, transferable representations from a large realworld dataset. We assess the generalizability of these learned representations across two wireless communications tasks: angle of arrival (AOA) estimation and automatic modulation classification (AMC). Our results show that carefully designed augmentations and diverse data enable contrastive learning to produce highquality, invariant latent representations. These representations are effective even with frozen encoder weights, and fine-tuning further enhances performance, surpassing supervised baselines. To the best of our knowledge, this is the first work to propose and demonstrate the effectiveness of self-supervised learning for radio signals across multiple tasks. Our findings highlight the potential of self-supervised learning to transform AI for wireless communications by reducing dependence on labeled data and improving model generalization - paving the way for scalable foundational 6G AI models and solutions.

2024

1. Penetration Testing of GSM Network using Man-In-The-Middle Attack

   Nosa Bello and Ogechukwu Kanu

   JES. Journal of Engineering Sciences, 2024

   Abs DOI

   Even though wireless communication technologies have advanced beyond the Global Systems for Mobile (GSM) Communications standard to mitigate its vulnerabilities, it is still a fallback technology when the coverage is limited and modern protocols aren’t available. There is a need for a comprehensive practical demonstration of the pools of vulnerabilities of the GSM architecture in the past decades using man-in-the-middle open-source tools and SDRs amidst the latest developments. It can be shown that an attacker can successfully carry out base station spoofing, IMSI catching, GSM packet sniffing, decoding, decryption and Denial of Service (DoS) attacks. Thus, this paper aims to comprehensively present practical demonstrations of the many vulnerabilities possible with available tools. We exploited IMSI catching with a rogue BTS deployed using OpenBTS and USRP B210, GSM sniffing and decoding using GR-GSM and RTL-SDR, and A5/1 decryption using clever thinking and rainbow tables. It was observed that the one-way authentication of the GSM protocol allows most mobile devices to easily authenticate to the rogue BTS with spoofed MCC/MNC and that the strongest signal mostly wins. Also, it was observed that the possibilities of attacks on the target user like a DoS, or unencrypted communication, can be successfully carried out because the rogue BTS is in total control. Though the vulnerabilities of GSM have been made known to the general public some network providers have not taken simple measures to mitigate them, thus this work can serve as a guideline for research purposes and an awareness to the general public.

2022

1. Building a Cost-effective Cellular Network using OpenBTS and USRP B210

   N. Bello and O.A. Kanu

   Nigerian Research Journal of Engineering and Environmental Sciences, Jun 2022

   Abs DOI

   The paper presents the development and implementation of a global system for mobile communication (GSM) network using OpenBTS and software-defined radio (SDR) that imitates the traditional GSM architecture. Compared to the traditional GSM architecture, the use of a software-based framework is cost-effective and useful for research in man-in-the-middle attacks. The paper provides a step-by-step installation of OpenBTS software, a software-based GSM architecture running on an Ubuntu 16.04 LTS operating system. The proposed setup was deployed and tested successfully and, in the end, subscribers were registered on the test network and given phone numbers that could make and receive phone calls and send text messages, which are regular features of the traditional GSM network.