ABSTRACT Supervised deep learning techniques have demonstrated potential for software vulnerability detection, yet their practical deployment is often constrained by the limited availability of high‐quality labelled data. Cross‐project vulnerability detection seeks to overcome this constraint by enabling knowledge transfer from labelled source projects to target projects with insufficient labels. Nevertheless, existing studies fail to fully leverage the discriminative knowledge of source‐domain models and overlook cross‐project local semantic inconsistencies. To tackle these issues, we propose KDSA‐VD, a cross‐project vulnerability detection approach that employs a dual‐driven fusion of knowledge distillation and structural alignment. Built on CodeBERT for code representation learning, the proposed method first acquires discriminative features through supervised training on source projects. It then enhances cross‐domain adaptation by integrating soft‐label distillation, consistency regularization, and structural alignment to better exploit unlabelled target‐project data. Experimental results on 12 cross‐project vulnerability detection tasks indicate that KDSA‐VD outperforms existing baseline methods in most settings and exhibits stable performance under varying target‐domain labelling conditions.

ABSTRACT Automated program repair (APR) aims to automatically detect and fix software defects, thereby improving software reliability and reducing debugging effort. Recently, researchers have explored the retrieval augmentation techniques to enhance large code models' performance in program repair. Existing retrieval augmentation models often inject retrieved information at the input layer, which can lead to input sequence inflation and interfere with the encoder's ability to focus on the core repair task. Meanwhile, learning‐based methods frequently produce unreliable patches, lacking mechanisms to verify or refine low‐confidence outputs during generation. To address these challenges, this paper proposes RADI‐PR, a novel approach that integrates retrieval augmentation and decoding intervention at the model's output layer. RADI‐PR dynamically incorporates relevant repair patterns based on historical fixes and intervenes in low‐confidence generations to enhance both the accuracy and reliability of generated patches. Comprehensive evaluations on four benchmark datasets, including Java, FixJS, Codeflaws and TSSB‐3 M, show that RADI‐PR consistently outperforms baseline methods. RADI‐PR achieves improvements of up to 5.5% in Precision, 3.2% in F1‐score and 2.2% in Accuracy.

Serverless computing has emerged as a promising deployment paradigm for edge scenarios, owing to its efficient resource utilization and flexible provisioning enabled by Function-as-a-Service (FaaS). In Serverless environment, developers are required to configure resources for functions to balance cost efficiency and performance. However, determining appropriate resource allocations for the functions running at the edge is a challenge due to the dynamic nature of the environment. This challenge is further compounded when managing serverless workflows composed of multiple interconnected functions with complex dependencies. To address such an challenge, we present FaaSAdapter, an efficient runtime resource configuration framework for workflow functions, aiming at conserving computational resources at the edge while ensuring timely response to user requests. Different from existing dynamic resource configuration methods that incrementally determine resource schemes for only the immediate subsequent workflow function, FaaSAdapter predicts the execution times of all the unexecuted functions across various resource configurations and determines an optimal configuration schema for the function instances based on the current execution progress. Then, it updates the configuration schema as needed during runtime. Comprehensive experiments demonstrate that FaaSAdapter ensures satisfactory response time of user requests with lowest resource consumption.

Large Language Models are widely utilized in natural language processing tasks but often necessitate expensive fine-tuning to accommodate specific domains. Parameter-efficient fine-tuning (PEFT) techniques help mitigate these costs by reducing the magnitude of trainable parameters. Meanwhile, some recent studies have employed Multi-Task Learning (MTL) to address issues of data scarcity and imbalance in PEFT, demonstrating its effectiveness in overcoming these challenges. The Mixture of Experts (MoE) approach further enhances knowledge sharing in MTL by dynamically assigning experts to different tasks. However, existing MoE approaches face challenges in accurately routing experts due to suboptimal routing methods and random routing. To address these limitations, we propose the Dual Routing Strategy for Mixture of Experts (DRMOE). DRMOE proposes a Dual Routing Strategy to refine expert allocation and constructs a Task-Specified Loss to alleviate randomness in routing decisions. Extensive experiments show that DRMOE effectively enhances performance across tasks, demonstrating its robustness in multi-task scenarios. The code is available at https://github.com/lhyscau/DRMOE.

Recently, Transformers have been introduced into the field of acoustics recognition. They are pre-trained on large-scale datasets using methods such as supervised learning and semi-supervised learning, demonstrating robust generality——It fine-tunes easily to down-stream tasks and shows more robust performance. However, the predominant fine-tuning method currently used is still full fine-tuning, which involves updating all parameters during training. This not only incurs significant memory usage and time costs but also compromises the model’s generality. Other fine-tuning methods either struggle to address this issue or fail to achieve matching performance. Therefore, we conducted a comprehensive analysis of existing fine-tuning methods and proposed an efficient fine-tuning approach based on Adapter tuning, namely AAT. The core idea is to freeze the audio Transformer model and insert extra learn-able Adapters, efficiently acquiring downstream task knowledge without compromising the model’s original generality. Extensive experiments have shown that our method achieves performance comparable to or even superior to full fine-tuning while optimizing only 7.118% of the parameters. It also demonstrates superiority over other fine-tuning methods.

As artificial intelligence (AI) continues to advance, AI-based audio systems are becoming increasingly vulnerable to adversarial attacks. However, most current studies overlook the scenes of environmental sounds and the imperceptibility of attack. In response to these, we propose a novel frequency-weighted perturbation algorithm for environmental sounds called the Frequency Psychological Attack Algorithm (FPAA). This innovative algorithm incorporates auditory thresholds with psychoacoustic principles during the perturbation generation process to create highly imperceptible adversarial examples. Extensive experiments conducted on two public datasets using multiple models demonstrate that our FPAA algorithm can produce adversarial audio examples that are not only imperceptible to the human ear but also maintain high offensive capability against AI-based audio systems.

Software defect prediction helps quality assurance teams find defects in software, thereby enhancing the reliability of the systems.In existing code-visualization-based defect prediction methods, challenges arise from mixing code information and the potential omission of critical defect features.To enhance the completeness of code features, this paper proposes a defect prediction model based on code grayscale pixel visualization with a fusion attention mechanism (Gpv2DP).Gpv2DP converts code into grayscale images and reshapes the images to a standard size, effectively alleviating the information loss problem caused by element mixing and image cropping.Furthermore, it constructs a code feature extracting network that simultaneously integrates the channel, spatial and 3D attention.We conduct empirical experiments on ten open-source Java projects from the PROMISE repository.The results show that the F-measure and AUC metrics of Gpv2DP outperform related defect prediction methods.

Software defect prediction aims to identify defect-prone code, aiding developers in optimizing testing resource allocation. Most defect prediction approaches primarily focus on coarse-grained, file-level defect prediction, which fails to provide developers with the precision required to locate defective code. Recently, some researchers have proposed fine-grained, line-level defect prediction methods. However, most of these approaches lack an in-depth consideration of the contextual semantics of code lines and neglect the local interaction information among code lines. To address the above issues, this paper presents a line-level defect prediction method grounded in a code bilinear attention fusion framework (BAFLineDP). This method discerns defective code files and lines by integrating source code line semantics, line-level context, and local interaction information between code lines and line-level context. Through an extensive analysis involving within- and cross-project defect prediction across 9 distinct projects encompassing 32 releases, our results demonstrate that BAFLineDP outperforms current advanced file-level and line-level defect prediction approaches.

Abstract In recent years, most video segmentation methods use deep CNN to process the input image, but they did not fully mine the rich intermediate predictions in spatio‐temporal space. And, the segmentation challenges such as occlusion, severe deformation and illumination have not been well solved so far. To alleviate these problems, this paper focuses on constructing multi module network structures that represent multi semantics and proposes a video object segmentation network via coupled‐stream architecture with feature memory mechanism. This network first extracts high‐level semantic features, edge features, long‐term and short‐term stable depth features of the target, and then decode them into the segmentation mask of target. In addition, negative skeleton inhibition and frame interpolation are used to prevent the interference of similar objects and motion blur, respectively. The method has a low GPU memory usage, regardless of the number of object in video. And performs 86.5%and 62.4% in J&F measure on DAVIS 2016 and DAVIS 2017 validation set, without fine‐tuning and online training.

Software defect prediction technology aids the reliability assurance team in identifying defect-prone code and assists the team in reasonably allocating limited testing resources. Recently, researchers assumed that the topological associations among code fragments could be harnessed to construct defect prediction models. Nevertheless, existing graph-based methods only concentrate on features of single-view association, which fail to fully capture the rich information hidden in the code. In addition, software defects may involve multiple code fragments simultaneously, but traditional binary graph structures are insufficient for representing these multivariate associations. To address these two challenges, this article proposes a multiview hypergraph representation learning approach (MVHR-DP) to amplify the potency of code features in defect prediction. MVHR-DP initiates by creating hypergraph structures for each code view, which are then amalgamated into a comprehensive fusion hypergraph. Following this, a hypergraph neural network is established to extract code features from multiple views and intricate associations, thereby enhancing the comprehensiveness of representation in the modeling data. Empirical study shows that the prediction model utilizing features generated by MVHR-DP exhibits superior area under the curve (AUC), F-measure, and matthews correlation coefficient (MCC) results compared to baseline approaches across within-project, cross-version, and cross-project prediction tasks.

Defects in software may result in system crashes, sluggish performance, or even deadlock, leading to the depletion of valuable resources. Implementing defect prediction can assist quality assurance teams in identifying potential software issues and rationalizing the allocation of testing resources, thereby decreasing the elimination of resources and enhancing software sustainability. Researchers have recently incorporated deep learning into defect prediction, extracting structural-semantic features from codes' abstract syntax trees (ASTs). However, inappropriate node granularity in ASTs may adversely impact the effectiveness of the extracted features. In addition, converting AST nodes into integer vectors may lead to the loss of structure information, resulting in poor model predictive capability. This paper proposes a tree-based encoding method with hybrid granularity for defect prediction to address these challenges. Specifically, five granularity selection schemes are extended to generate various ASTs from codes. Subsequently, a tree-based continuous bag-of-words model is utilized to map nodes of ASTs into numeric vector representations that conform to the tree-like structure of codes. The matrices converted from ASTs are then fed into a convolutional neural network to extract program features automatically. Experiments involving 24 versions of open-source projects demonstrate that our method can improve the effectiveness of extracted features in defect prediction tasks.

Code clone detection technology aims to automatically detect code similarity and help developers identify and reduce code duplication.While code syntax analysis-based methods are commonly used for clone detection, they may not capture semantic information due to bypassing the analysis of code text.To address this issue, this paper proposes a new method called visualization representation learning for code clone detection (VRL4CCD).This method converts source code fragments into grayscale images to preserve textual information and then utilizes VGG16 and a self-attention mechanism to extract features related to code semantic similarity.A siamese neural network is used to learn the similarity pattern between code features.Experimental results on the Big Clone Bench and Google Code Jam datasets demonstrate that VRL4CCD outperforms current clone detection methods regarding precision, recall, and F1-score, indicating the effectiveness of code visualization technology in clone detection tasks.

Defect prediction technology helps software quality assurance teams understand the distribution of software defects, which can assist them to allocate testing and verification resources appropriately. Current visualization-based software defect prediction methods lack spatial and global information of code images during the feature extraction process. To solve the problem of incomplete information, this paper proposes a Convolutional Neural Network with Global Self-Attention (CNN-GSA). The method converts codes into corresponding images and uses an improved convolutional neural network, which combines channel attention, spatial attention, and self-attention mechanisms in a global attention layer, to extract defect-related structural and semantic features in code images. Empirical study shows that the model built with the features generated by CNN-GSA can achieve better F-measure results in defect prediction tasks.

Abstract Due to the differentiation between training and testing data in the feature space, cross‐project defect prediction (CPDP) remains unaddressed within the field of traditional machine learning. Recently, transfer learning has become a research hot‐spot for building classifiers in the target domain using the data from the related source domains. To implement better CPDP models, recent studies focus on either feature transferring or instance transferring to weaken the impact of irrelevant cross‐project data. Instead, this work proposes a dual weighting mechanism to aid the learning process, considering both feature transferring and instance transferring. In our method, a local data gravitation between source and target domains determines instance weight, while features that are highly correlated with the learning task, uncorrelated with other features and minimizing the difference between the domains are rewarded with a higher feature weight. Experiments on 25 real‐world datasets indicate that the proposed approach outperforms the existing CPDP methods in most cases. By assigning weights based on the different contribution of features and instances to the predictor, the proposed approach is able to build a better CPDP model and demonstrates substantial improvements over the state‐of‐the‐art CPDP models.

Software quality plays an important role in the software lifecycle. Traditional software defect prediction approaches mainly focused on using hand‐crafted features to detect defects. However, like human languages, programming languages contain rich semantic and structural information, and the cause of defective code is closely related to its context. Failing to catch this significant information, the performance of traditional approaches is far from satisfactory. In this study, the authors leveraged a long short‐term memory (LSTM) network to automatically learn the semantic and contextual features from the source code. Specifically, they first extract the program's Abstract Syntax Trees (ASTs), which is made up of AST nodes, and then evaluate what and how much information they can preserve for several node types. They traverse the AST of each file and fed them into the LSTM network to automatically the semantic and contextual features of the program, which is then used to determine whether the file is defective. Experimental results on several opensource projects showed that the proposed LSTM method is superior to the state‐of‐the‐art methods.

Although the machine learning-based software defect prediction (SDP) method has shown promising value in software engineering, yet challenges remain.To improve the performance of SDP, some researchers have used deep learning algorithms to extract the semantic and structural features of the program.However, in more practical cross-project defect prediction (CPDP) tasks, whether deep learning-generated features can be directly used should be explored due to the data distribution shift that usually exists in different projects.In this paper, we propose a Transferable Hybrid Features Learning with Convolutional Neural Network (CNN-THFL) framework to conduct CPDP.Specially, CNN-THFL mines deep learning-generated features from token vectors extracted from programs' abstract syntax trees via convolutional neural network.Furthermore, CNN-THFL learns the transferable joint features simultaneously considering deep learning-generated and handcrafted features by applying a transfer component analysis algorithm.Finally, the features generated by CNN-THFL are fed to the classifier to train a defect prediction model.Extensive experiments verify that CNN-THFL can outperform referential methods on 72 pairs of CPDP tasks formed by 9 open-source projects.

Using classification methods to predict software defect is receiving a great deal of attention and most of the existing studies primarily conduct prediction under the within‐project setting. However, there usually had no or very limited labelled data to train an effective prediction model at an early phase of the software lifecycle. Thus, cross‐project defect prediction (CPDP) is proposed as an alternative solution, which is learning a defect predictor for a target project by using labelled data from a source project. Differing from previous CPDP methods that mainly apply instances selection and classifiers adjustment to improve the performance, in this study, the authors put forward a novel distribution–adaptation‐based CPDP approach, joint distribution matching (JDM). Specifically, JDM aims to minimise the joint distribution divergence between the source and target project to improve the CPDP performance. By constructing an adaptive weight vector for the instances of the source project, JDM can be effective and robust at reducing marginal distribution discrepancy and conditional distribution discrepancy simultaneously. Extensive experiments verify that JDM can outperform related distribution–adaptation‐based methods on 15 open‐source projects that are derived from two types of repositories.

Machine-learning-based software defect prediction (SDP) methods are receiving great attention from the researchers of intelligent software engineering. Most existing SDP methods are performed under a within-project setting. However, there usually is little to no within-project training data to learn an available supervised prediction model for a new SDP task. Therefore, cross-project defect prediction (CPDP), which uses labeled data of source projects to learn a defect predictor for a target project, was proposed as a practical SDP solution. In real CPDP tasks, the class imbalance problem is ubiquitous and has a great impact on performance of the CPDP models. Unlike previous studies that focus on subsampling and individual methods, this study investigated 15 imbalanced learning methods for CPDP tasks, especially for assessing the effectiveness of imbalanced ensemble learning (IEL) methods. We evaluated the 15 methods by extensive experiments on 31 open-source projects derived from five datasets. Through analyzing a total of 37504 results, we found that in most cases, the IEL method that combined under-sampling and bagging approaches will be more effective than the other investigated methods.

Software defect prediction (SDP) technology is receiving widely attention and most of SDP models are trained on data from the same project. However, at an early phase of the software lifecycle, there are little to no within‐project training data to learn an available supervised defect‐prediction model. Thus, cross‐project defect prediction (CPDP), which is learning a defect predictor for a target project by using labelled data from a source project, has shown promising value in SDP. To better perform the CPDP, most current studies focus on filtering instances or selecting features to weaken the impact of irrelevant cross‐project data. Instead, the authors propose a novel multiple‐components weights (MCWs) learning model to analyse the varying auxiliary power of multiple components in a source project to construct a more precise ensemble classifiers for a target project. By combining the MCW model with kernel mean matching algorithm, their proposed approach adjusts the source‐instance weights and source‐component weights to jointly alleviate the negative impacts of irrelevant cross‐project data. They conducted comprehensive experiments by employing 15 real‐world datasets to demonstrate the advantages and effectiveness of their proposed approach.