No abstract

No abstract

Predicting defects during software testing reduces an enormous amount of testing effort and help to deliver a high‐quality software system. Owing to the skewed distribution of public datasets, software defect prediction (SDP) suffers from the class imbalance problem, which leads to unsatisfactory results. Overfitting is also one of the biggest challenges for SDP. In this study, the authors performed an empirical study of these two problems and investigated their probable solution. They have conducted 4840 experiments over five different classifiers using eight NASA projects and 14 PROMISE repository datasets. They suggested and investigated the varying kernel function of an extreme learning machine (ELM) along with kernel principal component analysis (K‐PCA) and found better results compared with other classical SDP models. They used the synthetic minority oversampling technique as a sampling method to address class imbalance problems and k‐fold cross‐validation to avoid the overfitting problem. They found ELM‐based SDP has a high receiver operating characteristic curve over 11 out of 22 datasets. The proposed model has higher precision and F‐score values over ten and nine, respectively, compared with other state‐of‐the‐art models. The Mathews correlation coefficient (MCC) of 17 datasets of the proposed model surpasses other classical models' MCC.

An important characteristic of recent MPC protocols is an input-independent setup phase in which most computations are offloaded, which greatly reduces the execution overhead of the online phase where parties provide their inputs. For a very efficient evaluation of arithmetic circuits in an information-theoretic online phase, the MPC protocols consume Beaver multiplication triples generated in the setup phase. Triple generation is generally the most expensive part of the protocol, and improving its efficiency is the aim of our work. We specifically focus on computation over rings of the form Z 2 in the semi-honest model and the two-party setting, for which an Oblivious Transfer (OT)-based protocol is currently the best solution. To improve upon this method, we propose a protocol based on RLWE-based Additively Homomorphic Encryption. Our experiments show that our protocol is more scalable, and it outperforms the OT-based protocol in most cases. For example, we improve communication by up to 6.9x and runtime by up to 3.6x for 64-bit triple generation.

No abstract