Class imbalance is a prevalent problem in machine learning which affects the prediction performance of classification algorithms. Software Defect Prediction (SDP) is no exception to this latent problem. Solutions such as data sampling and ensemble methods have been proposed to address the class imbalance problem in SDP. This study proposes a combination of Synthetic Minority Oversampling Technique (SMOTE) and homogeneous ensemble (Bagging and Boosting) methods for predicting software defects. The proposed approach was implemented using Decision Tree (DT) and Bayesian Network (BN) as base classifiers on defects datasets acquired from NASA software corpus. The experimental results showed that the proposed approach outperformed other experimental methods. High accuracy of 86.8% and area under operating receiver characteristics curve value of 0.93% achieved by the proposed technique affirmed its ability to differentiate between the defective and non-defective labels without bias.

No abstract

Cryptographic techniques have been widely employed to protect sensitive data from unauthorized access and manipulation. Among these cryptographic techniques, Data Encryption Standard (DES) has been widely employed, however, it suffers from key and differential attacks. To overcome these attacks, several DES modifications have been proposed in literatures. Most modifications have focused on enhancing DES encryption key; however, the strength of a cryptographic technique is determined by the encryption key used and the number of encryption rounds. It is a known fact that Advanced Encryption Standard (AES) cryptographic technique with 14 encryption rounds is stronger than AES with 12 rounds while AES with 12 rounds is stronger than AES with 10 rounds. Therefore, this study proposed a DES cryptographic technique whose number of rounds is dynamic. Users are expected to specify the number of encryption and decryption rounds to be employed at run time. Moreover, a predefined number of shifting operations which is left circular shift 2 was chosen for each encryption round. As, a trade-off in complexity, the number of Substitution box (S-box) was also reduced to 4, so that the input to the S-boxes would be arranged in four 12-bit blocks for the X-OR operation and not six 8-bit blocks as in the traditional DES. Finally, three keys were used to encrypt, decrypt and encrypt the plaintext ciphertext as in triple DES. The modified DES yielded a better avalanche effect for rounds greater than 16 though its encryption and decryption time were greater than that of the traditional DES.

No abstract

The phishing attack is one of the most complex threats that have put internet users and legitimate web resource owners at risk. The recent rise in the number of phishing attacks has instilled distrust in legitimate internet users, making them feel less safe even in the presence of powerful antivirus apps. Reports of a rise in financial damages as a result of phishing website attacks have caused grave concern. Several methods, including blacklists and machine learning-based models, have been proposed to combat phishing website attacks. The blacklist antiphishing method has been faulted for failure to detect new phishing URLs due to its reliance on compiled blacklisted phishing URLs. Many ML methods for detecting phishing websites have been reported with relatively low detection accuracy and high false alarm. Hence, this research proposed a Functional Tree (FT) based metalearning models for detecting phishing websites. That is, this study investigated improving the phishing website detection using empirical analysis of FT and its variants. The proposed models outperformed baseline classifiers, meta-learners and hybrid models that are used for phishing websites detection in existing studies. Besides, the proposed FT based meta-learners are effective for detecting legitimate and phishing websites with accuracy as high as 98.51% and a false positive rate as low as 0.015. Hence, the deployment and adoption of FT and its metalearner variants for phishing website detection and applicable cybersecurity attacks are recommended.