No abstract

No abstract

Autodect framework protects management information systems (MIS) and databases from user input SQL injection attacks. This framework overcomes intrusion or penetration into the system by automatically detecting and preventing attacks from the user input end. The attack intentions is also known since                 it is linked to a proxy database, which has a normal and abnormal code vector profiles that      helps to gather information about the intent as well as knowing the areas of interest while conducting the attack. The information about the attack is forwarded to Autodect knowledge base (database), meaning that any successive attacks from the proxy database will be compared to the existing attack pattern logs in the knowledge base, in future this knowledge base-driven database will help organizations to analyze trends of attackers, profile them and deter them. The research evaluated the existing security frameworks used to prevent user input SQL injection; analysis was also done on the factors that lead to the detection of SQL injection. This knowledge-based framework     is able to predict the end goal of any injected attack vector. (Known and unknown signatures). Experiments were conducted on true and simulation websites and open-source datasets to analyze the performance and a comparison drawn between the Autodect framework and other existing tools. The research showed that Autodect framework has an accuracy level of 0.98. The research found a gap that all existing tools and frameworks never came up with a standard datasets for sql injection, neither do we have a universally accepted standard data set.

Epilepsy is a condition that disrupts normal brain function and sometimes leads to seizures, unusual sensations, and temporary loss of awareness. Electroencephalograph (EEG) records are commonly used for diagnosing epilepsy, but traditional analysis is subjective and prone to misclassification. Previous studies applied Deep Learning (DL) techniques to improve EEG classification, but their performance has been limited due to dynamic and non-stationary nature of EEG structure. In this paper, we propose a multi-channel EEG classification model called LConvNet, which combines Convolutional Neural Networks (CNN) for spatial feature extraction and Long Short-Term Memory (LSTM) for capturing temporal dependencies. The model is trained using open source secondary EEG data from Temple University Hospital (TUH) to distinguish between epileptic and healthy EEG signals. Our model achieved an impressive accuracy of 97%, surpassing existing EEG classification models used in similar tasks such as EEGNet, DeepConvNet and ShallowConvNet that had 86%, 96% and 78% respectively. Furthermore, our model demonstrated impressive performance in terms of trainability, scalability and parameter efficiency during additional evaluations.

No abstract