W. Eric Wong’s research while affiliated with University of Texas at Dallas and other places

Software fault localization remains challenging due to limited feature diversity and low precision in traditional methods. This paper proposes a novel approach that integrates multi-objective optimization with deep learning models to improve both accuracy and efficiency in fault localization (FL). By framing feature selection as a multi-objective optimization problem (MOP), we extract and fuse three critical fault-related feature sets: spectrum-based, mutation-based, and text-based features, into a comprehensive feature fusion model. These features are then embedded within a deep learning architecture, comprising a multilayer perceptron (MLP) and gated recurrent network (GRN), which together enhance localization accuracy and generalizability. Experiments on the Defects4J benchmark dataset with 434 faults show that the proposed algorithm reduces processing time by 78.2% compared to single-objective methods. Additionally, our MLP and GRN models achieve a 94.2% improvement in localization accuracy compared to traditional FL methods, outperforming state-of-the-art deep learning-based FL method by 7.67%. Further validation using the PROMISE dataset demonstrates the generalizability of the proposed model, showing a 4.6% accuracy improvement in cross-project tests over state-of-the-art deep learning-based FL method.

To ensure the reliability of DNN systems and address the test generation problem for neural networks, this paper proposes a fuzzing test generation technique based on many-objective optimization algorithms. Traditional fuzz testing employs random search, leading to lower testing efficiency and tends to generate numerous invalid test cases. By utilizing many-objective optimization techniques, effective test cases can be generated. To achieve high test coverage, this paper proposes several improvement strategies. The frequency-based fuzz sampling strategy assigns priorities based on the frequency of selection of initial data, avoiding the repetitive selection of the same data and enhancing the quality of initial data better than random sampling strategies. To address the issue that global search may yield test not satisfying semantic constraints, a local search strategy based on the Monte Carlo tree search is proposed to enhance the algorithm's local search capabilities. Furthermore, we improve the diversity of the population and the algorithm's global search capability by updating SPEA2's external archive based on a decomposition-based archiving strategy. To validate the effectiveness of the proposed approach, experiments were conducted on several public datasets and various neural network models. The results reveal that, compared to random and clustering-based sampling, the frequency-based fuzz sampling strategy provides a greater improvement in coverage rate in the later stages of iterations. On complex networks like VGG16, the improved SPEA2 algorithm increased the coverage rate by about 12% across several coverage metrics, and by approximately 40% on LeNet series networks. The experimental results also indicates that the newly generated test cases not only exhibit higher coverage rates but also generate adversarial samples that reveal model errors.

Accurate early prediction of software defects is essential to maintain software quality and reduce maintenance costs. However, the field of software defect prediction (SDP) faces challenges such as class imbalances, high-dimensional feature spaces, and suboptimal prediction accuracy. To mitigate these challenges, this paper introduces a novel SDP framework that integrates hybrid sampling techniques, specifically Borderline SMOTE and Tomek Links, with a suite of multi-objective optimization algorithms, including NSGA-II, MOPSO, and MODE. The proposed model applies feature fusion through multi-objective optimization, enhancing both the generalization capability and stability of the predictions. Furthermore, the integration of parallel processing for these optimization algorithms significantly boosts the computational efficiency of the model. Comprehensive experiments conducted on datasets from NASA and PROMISE repositories demonstrate that the proposed hybrid sampling and multi-objective optimization approach improves data balance, eliminates redundant features, and enhances prediction accuracy. The experimental results also highlight the robustness of the feature fusion approach, confirming its superiority over existing state-of-the-art techniques in terms of predictive performance and applicability across diverse datasets.

The 1980s and 1990s were a “golden age” for deep thinkers on the topic of software reliability models and testing. But today that thought leadership has disappeared. In this virtual roundtable we ask, “What happened?”

This paper introduces a method for detecting vulnerabilities in smart contracts using static analysis and a multi-objective optimization algorithm. We focus on four types of vulnerabilities: reentrancy, call stack overflow, integer overflow, and timestamp dependencies. Initially, smart contracts are compiled into an abstract syntax tree to analyze relationships between contracts and functions, including calls, inheritance, and data flow. These analyses are transformed into static evaluations and intermediate representations that reveal internal relations. Based on these representations, we examine contract's functions, variables, and data dependencies to detect the specified vulnerabilities. To enhance detection accuracy and coverage, we apply a multi-objective optimization algorithm to the static analysis process. This involves assigning initial numeric values to input data and monitoring changes in statement coverage and detection accuracy. Using coverage and accuracy as fitness values, we calculate Pareto front and crowding distance values to select the best individuals for the new parent population, iterating until optimization criteria are met. We validate our approach using an open-source dataset collected from Etherscan, containing 6,693 smart contracts. Experimental results show that our method outperforms state-of-the-art tools in terms of coverage, accuracy, efficiency, and effectiveness in detecting the targeted vulnerabilities.

AI and ML have been applied ubiquitously to our everyday lives. The impact has also become overwhelming. How to certify and regulate these applications to avoid unintentional or on-purpose harm is an essential topic that must be addressed.

Effective software defect prediction (SDP) is important for software quality assurance. Numerous advanced SDP methods have been proposed recently. However, how to consider the task correlations and achieve multi-objective SDP accurately and efficiently still remains to be further explored. In this paper, we propose a novel multi-objective SDP method via multi-source uncertain information fusion and multi-task multi-view learning (MTMV) to accurately and efficiently predict the proneness, location, and type of defects. Firstly, multi-view features are extracted from multi-source static analysis results, reflecting uncertain defect location distribution and semantic information. Then, a novel MTMV model is proposed to fully fuse the uncertain defect information in multi-view features and realize effective multi-objective SDP. Specifically, the convolutional GRU encoders capture the consistency and complementarity of multi-source defect information to automatically filter the noise of false and missed alarms, and reduce location and type uncertainty of static analysis results. A global attention mechanism combined with the hard parameter sharing in MTMV fuse features according to their global importance of all tasks for balanced learning. Then, considering the latent task and feature correlations, multiple task-specific decoders jointly optimize all SDP tasks by sharing the learning experience. Through the extensive experiments on 14 datasets, the proposed method significantly improves the prediction performance over 12 baseline methods for all SDP objectives. The average improvements are 30.7%, 31.2%, and 32.4% for defect proneness, location, and type prediction, respectively. Therefore, the proposed multi-objective SDP method can provide more sufficient and precise insights for developers to significantly improve the efficiency of software analysis and testing.