Unstructured Supplementary Services Data (USSD) is a menu driven, real time communication technology used for value added services. It is adopted by banks for financial transactions due to its ease of operation. However existing USSD are used by fraudster to commit identity theft through Subscriber Identification Module (SIM) swap, phone theft and kidnap, in other to access funds in the bank. One of the reasons this is made possible is because existing USSD platforms use Automated Teller Machine (ATM) Personal Identification Number (PIN) as second level authenticator and this compromises the ATM channel and violets one of the stated guidelines for USSD operation in Nigeria. More so, the PIN is entered bare on the platform and so can easily be stolen by shoulder surfing. Therefore, in this paper we developed and simulated an improved USSD security model for banking operations in Nigeria. The security of existing USSD platform was enhanced using answer to a secret question as another level of authentication. This was with the view to minimise identity theft. This secret question is registered in the bank during account opening for new customers while existing customers will have to update their details in the banks data base before registering for USSD services. This is done the same way customers verify their ATM PIN in the bank. Hence the answer is known by the customer alone. The model was implemented using php on XAMPP platform and simulated using hubtel USSD mocker. Results showed that security of the proposed system was enhanced through another level of authentication provided by the answer to the security question.

Fake-news refers to a cyber-weapon launched through the social media, as, its consequence can result to the breakdown of law and order in the society both physically and on the cyber-social-space. In Nigeria, there is currently no established law that guides the use of social media. Therefore, the rate at which fake-news propagates is alarming. This paper presents a new dataset, with focus on Nigeria’s trending news such as EndSARS and Herdsmen attacks, which was further used to simulate Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) machine learning models to detect fake-news. The data were extracted from twitter using twitter Application Package Interface (API) and from facebook using a scraping tool. The dataset was encoded using Unicode escape function in python to make all characters accessible by the algorithm and tokenised using Global Vectors for Word Representation. The dataset was used to train CNN and RNN models built in python on google colab platform to detect fake-news using accuracy, sensitivity, recall and F1 score as evaluation metrics. Results showed that RNN performed better in terms of accuracy and precision, at 82.34% and 93.19% compared to 81.96% and 79.65% for CNN, F1 scores are approximately the same for both models and CNN performed better than RNN in terms of recall at 98.03% to 50.61% for RNN.