Abstract Software defect prediction (SDP) is crucial for enhancing software quality and reducing development costs. Prevailing SDP methods often depend on traditional code metrics, which inadequately capture vital semantic information from source code, thereby limiting defect identification accuracy. This paper introduces DP-S3, a novel SDP model that integrates features from abstract syntax trees (ASTs), program slices, and standard metrics. DP-S3 extracts ASTs and program slices, transforming them into vector representations. A hierarchical long short-term memory network then learns semantic features from these vectors, which are combined with standard metrics from the PROMISE repository. A key innovation is our feature fusion strategy employing a channel self-attention mechanism to dynamically weight the three feature sets. We evaluated DP-S3 on seven open-source Java projects from the Apache repository against several state-of-the-art methods. The results demonstrate DP-S3’s superior performance, achieving average improvements of up to 3.8% in area under the receiver operating characteristic curve, 4.5% in F1, and 7.5% in Matthews correlation coefficient over baselines, showcasing its effectiveness. Key limitations include its current focus on Java projects and within-project defect prediction. Nevertheless, this work concludes that a synergistic fusion of syntactic, semantic (slice-based), and traditional metric features, guided by attention mechanisms, significantly enhances SDP capabilities and offers a promising direction for future research.

Abstract The widespread adoption of encryption in network traffic significantly challenges traditional detection methods that rely on payload analysis. Existing approaches often convert traffic into images or sequences for deep learning models, producing redundant features and struggling with multi-protocol environments. In this study, we propose HEAT (Header-Embedded Attention for Traffic Detection), a novel model that leverages packet header fields to develop a robust characteristic representation for encrypted traffic analysis. HEAT introduces a hierarchical attention mechanism combined with a novel contextual embedding technique that enhances the semantic representation of header field values. Additionally, HEAT integrates an adapted Kolmogorov–Arnold Network classifier with B-spline activations and L1 weight regularization, optimizing the model for efficient real-time processing. Extensive evaluations on CICIDS-2018, Stratosphere, and ISCX2012 datasets demonstrate HEAT’s superior performance, achieving 98.95% accuracy and 98.28% F1-score on CICIDS-2018, 99.5% accuracy and 98.54% F1-score on Stratosphere, and 99.75% accuracy with 99.25% F1-score on ISCX2012. HEAT significantly outperforms CNN, LSTM, and BiGRU baselines. Moreover, it maintains detection accuracy above 98.95% during incremental learning, with only a 0.9% F1-score drop, compared with 6.55% in conventional models. These results highlight HEAT’s novelty, stability, and adaptability, making it a scalable and robust solution for encrypted malicious traffic detection.

The growing prevalence of encrypted malicious network traffic poses significant challenges for cybersecurity, as it conceals the content from traditional detection methods. Temporal convolutional networks (TCNs) present promising capabilities for extracting complex temporal features and patterns from the dynamic traffic flow data. However, the unidirectional nature of traditional TCNs limits their effectiveness in capturing the full context of network traffic, which often exhibits bidirectional temporal dependencies. Consequently, a few studies have proposed bidirectional TCN (BiTCN) architectures to address the limitations. However, these methods present complex architectures that require a significant amount of parameters to be learned, which imposes high memory requirements on the computational resources for training such models. In this study, we introduce the efficient bidirectional TCN (eBiTCN) model, an efficient BiTCN that requires fewer parameters yet not at the expense of computational cost and effective detection. The eBiTCN framework combines a bidirectional processor, a lightweight gating mechanism, temporal attention, dropout, a novel loss function, and dense layers. Extensive experiments show that eBiTCN outperforms eight state-of-the-art competing models in terms of detection efficacy, speed, and scalability. The eBiTCN model showcased robust performance in detecting evolving attacks and excelled across various real-world datasets. Its efficiency in training speed and reduced memory usage translates to lower infrastructure costs, making it an accessible and effective choice for deployment. These findings highlight eBiTCN’s practicality and dependability in addressing contemporary network security needs.

Test case prioritization techniques improve the fault detection rate by adjusting the execution sequence of test cases. For static black‐box test case prioritization techniques, existing methods generally improve the fault detection rate by increasing the early diversity of execution sequences based on string distance differences. However, such methods have a high time overhead and are less stable. This paper proposes a novel test case prioritization method (DC‐TCP) based on density‐based spatial clustering of applications with noise (DBSCAN) and combination policies. By introducing a combination strategy to model the inputs to generate a mapping model, the test inputs are mapped to consistent types to improve generality. The DBSCAN method is then used to refine the classification of test cases further, and finally, the Firefly search strategy is introduced to improve the effectiveness of sequence merging. Extensive experimental results demonstrate that the proposed DC‐TCP method outperforms other methods in terms of the average percentage of faults detected and exhibits advantages in terms of time efficiency when compared to several existing static black‐box sorting methods.

Summary Although cross‐project defect prediction (CPDP) techniques that use traditional manual features to build defect prediction model have been well‐developed, they usually ignore the semantic and structural information inside the program and fail to capture the hidden features that are critical for program category prediction, resulting in poor defect prediction results. Researchers have proposed using deep learning to automatically extract the semantic features of programs and fuse them with traditional features as training data. However, in practice, it is important to explore the effective representation of the semantic features in the programs and how the fusion of a reasonable ratio between the two types of features can maximize the effectiveness of the model. In this paper, we propose a semantic feature enhancement‐based defect prediction framework (SFE‐DP), which augments the semantic feature set extracted from the program code with data. We also introduce a layer of self‐attentive mechanism and a matching layer to filter low‐efficiency and non‐critical semantic features in the model structure. Finally, we combine the idea of hybrid loss function to iteratively optimize the model parameters. Extensive experiments validate that SFE‐DP can outperform the baseline approaches on 90 pairs of CPDP tasks formed by 10 open‐source projects.

Online Social Networks (OSNs) face escalating security threats that imperil user privacy. Conventional Deep Learning methods, relying predominantly on fixed learning rates, encounter limitations when capturing the nuanced intricacies of OSN traffic that arise from shifting user behaviors, diverse content types, and evolving interaction patterns because of social trending topics changes. To tackle these challenges, our paper delves into the diverse variations and transitions from a uniform approach, where a single method is employed for various types of data, to a multi-variation methodology. This methodology dynamically adapts to the special characteristics of each data type, resulting in more effective data representation while alleviating the limitations associated with fixed-rate calibration. Therefore, we devise the Adaptive Swarm Reinforcement Learning (ASRL) method that leverages adaptive learning to intricately analyze a wide range of user interactions, endowing our proposed method with the capacity to flexibly adjust to the constantly shifting OSN patterns. The experiments show that the proposed ASRL method achieves an accuracy of 98.59% in detecting a range of threat patterns, surpassing other prevalent methods by an average of 5% across the datasets from Facebook, Google+, and Twitter. Meanwhile, ASRL logs suspicious activities to identify the intruder for forensic analysis. The implementation of our proposed method is now publicly accessible athttps://github.com/don2c/asrl_Project.

With the rapid advancements in internet technology, the complexity and sophistication of network traffic attacks are increasing, making it challenging for traditional anomaly detection systems to analyze and detect malicious network attacks. The increasing advancedness of cyber threats calls for innovative approaches to identify malicious patterns within network traffic precisely. The primary issue lies in the fact that these approaches do not focus on the essential adaptive features of network traffic. We proposed an effective anomaly detection system for malicious network traffic attacks called the Deep Ensemble Learning Model (DELM). We leverage the structure of the Feedforward Deep Neural Network (FDNN), and Deep Belief Network (DBN), incorporating multiple hidden layers with non-linear activation functions. Integrating Adaptive Feature Aggregation (AFA) with the FDNN algorithm dynamically adjusts the feature aggregation process based on incoming traffic characteristics to improve adaptability. The Conditional Generative Network was employed to enhance DELM for generating data for minority classes. To improve the model’s accuracy, we applied batch normalization and data augmentation techniques for preprocessing, utilized n-gram, one-hot encoding, and feature aggregation methods for effective feature extraction. This study significantly contributes to network security by enhancing systems for detecting malicious network traffic. With its interpretability and adaptability, our proposed model shows promise in addressing the evolving cyber threat and fortifying critical network infrastructure. The experimental results demonstrate that our model performs with higher stability than the existing state-of-the-art detection approaches, as reflected by its higher accuracy, precision, recall, F1-score, and AUC-ROC.

Recommendation systems provide ease and convenience for users to address information overload problems while interacting with online platforms such as social media and e-commerce. However, it raises several questions about privacy, especially for users who prefer to remain anonymous, especially on online social networks (OSNs). Moreover, due to the commercialization of online users' data, some service providers sell users' data to third parties at the blind side of the users, which leads to trust issues between users and service providers. Such matters call for a system that gives online users much-needed control and autonomy of their data. With the advancement of blockchain technology, many research institutions are experimenting with decentralized technologies to resolve the OSN user dilemma of privacy intrusion against third parties and hacks. To resolve these limitations, we propose RecGuard, a privacy preservation blockchain-based network system. We developed two smart contracts, RG-SH and RG-ST, to ensure the security and privacy of user data. The RG-SH manages user data, whereas the RG-ST stores data. A graph convolutional network (GCN) was integrated with the blockchain-based system to detect malicious nodes. Finally, we implemented our framework prototype on a locally simulated network. The analysis and experiment results show that the proposed scheme demonstrates the effectiveness and privacy of users in our framework.