Abstract:K-clique enumeration is an important problem in subgraph matching, and the bitmap algorithm has been proven to be an effective method for solving the K-clique enumeration problem. Currently, state-of-the-art K-clique enumeration algorithms are accelerated by GPU. Previous studies have not investigated the impact of sparsity in real-world graph data on bitmap-based K-clique enumeration algorithms. Instead, static parallelization methods and bitmap construction strategies are commonly used on GPU, which result in low computational efficiency. This study proposes a thread-parallel load-balancing scheduling algorithm for bitmap tasks, which resolves the thread divergence problem while achieving high parallelism in the bitmap algorithm. Furthermore, it introduces a dynamic bitmap construction algorithm, enabling bitmaps to be constructed and activated at appropriate times for efficient execution of the bitmap algorithm. A GPU-friendly K-clique enumeration system, KCMiner, is implemented, which adaptively selects optimization strategies for K-clique enumeration tasks. Experimental results on GPU platforms show that the proposed method achieves up to 7.36 times speedup over the baseline K-clique enumeration algorithm and up to 30.2 times speedup over the baseline subgraph matching system.

Abstract:The heuristic test case generation method that combines machine learning-related technologies can significantly improve the test efficiency. Existing studies focus on building efficient surrogate models with partial test cases, but ignore the influence of both the initial population quality and surrogate models on the multi-path testing efficiency. Therefore, this study proposes a test case reduction and generation method combining K-means and support vector machine regression (SVR). The randomly generated test cases are clustered into several clusters by adopting K-means, and only the test cases that are within a particular distance away from the cluster center are retained, with the path coverage matrix for these test cases constructed. This matrix is employed to evaluate the path coverage potential of test cases and the coverage difficulty of paths. Additionally, based on these two conditions, the test cases are ranked, and several test cases are selected from different clusters to construct the test case reduction set, which is taken as the initial genetic population. This not only increases the diversity of the initial population and reduces its redundancy, but also helps to reduce the iteration number for multi-path coverage test cases. Meanwhile, the test cases before clustering and their fitness are employed as the samples to train the SVR fitness prediction model designed for multi-path coverage, and then the new test cases generated by genetic evolution are utilized to update the model, thus improving the model accuracy and reducing the time consumed due to the instrumentation program execution. In this way, both population quality and test efficiency can be improved. The experimental results show that on fifteen programs, the proposed method has better improvements in terms of indicators such as the coverage rate and average evolutionary generation. Specifically, in terms of the coverage rate, the proposed method demonstrates an improvement of at least 7% and up to 49% compared to three types of baseline methods, and shows the enhancement of approximately 10% to a maximum of 25% compared to five competitive methods. The proposed method provides guidance for the research on multi-path testing that combines machine learning.

Abstract:The black-box vulnerability scanner is an essential tool for Web application vulnerability detection, capable of identifying potential security threats effectively before a Web application is launched, thus enhancing the overall security of the application. However, most current black-box scanners primarily collect the attack surface through user operation simulation and regular expression matching. The simulation of user operations is vulnerable to interception by input validation mechanisms and struggles with handling complex event operations, while regular expression matching is ineffective in processing dynamic content. As a result, the scanner cannot effectively address hidden attack surfaces within JavaScript code or dynamically generated attack surfaces, leading to suboptimal vulnerability detection in some Web applications. To resolve these issues, this study proposes a JavaScript exposure scanner (JSEScan), a vulnerability scanner enhancement framework based on JavaScript code analysis. The framework integrates static and dynamic code analysis techniques, bypassing form validation and event-triggering restrictions. By extracting attack surface features from JavaScript code, JSEScan identifies attack surfaces and synchronizes them across multiple scanners, enhancing their vulnerability detection capabilities. The experimental results demonstrate that JSEScan increases coverage by 81.02% to 242.15% compared to using a single scanner and uncovers an additional 239 security vulnerabilities when compared to multiple scanners working concurrently, showing superior attack surface collection and vulnerability detection capabilities.

Abstract:With the rapid development of the HarmonyOS ecosystem, security issues related to HarmonyOS applications have gradually become a key research focus. In the Android domain, various mature static analysis frameworks have been widely applied to security detection tasks. However, static analysis frameworks for HarmonyOS applications are still in the early stages of development. The OpenHarmony community is currently working on static analysis based on the source code of HarmonyOS applications using ArkTS. However, in practical security detection tasks, obtaining application source code is often difficult, which limits the applicability of this approach. To address this challenge, this study proposes a static analysis framework for HarmonyOS applications based on the Ark intermediate representation (Panda IR). This framework provides basic information interfaces for Panda IR, designs a field-sensitive pointer analysis algorithm tailored to ArkTS syntax features, and implements extended analysis interfaces that interact with pointer analysis. Specifically, 318 instructions in Panda IR are semantically categorized and processed, and a customized pointer flow graph design is further developed. To support ArkTS syntax features, new propagation rules for pointer sets are introduced, and the semantics of special calls are accurately modeled. In addition, based on the pointer analysis results, inter-procedural data dependencies are optimized, and alias analysis capabilities are provided. The experimental evaluation of HarmonyFlow covers three aspects: ArkTS syntax feature coverage, pointer analysis accuracy, and pointer analysis speed. Experimental results show that HarmonyFlow can correctly handle key ArkTS syntax features. The precision and recall rates for call-edge identification in 9 open-source HarmonyOS applications are 98.33% and 92.22%, respectively, with an average runtime of 96 s for 35 real-world HarmonyOS applications.

Abstract:Scade is a well-known commercial tool widely used in the development of safety-critical embedded control software, whose modeling language is a synchronous language extended from Lustre, a synchronous data-flow language. Correct compilation of synchronous languages, including Lustre, has attracted much attention in recent years, and has been addressed in many studies through formal verification. To build a formally verified compiler for such a language, it is a common practice to compile the source program into a C-like program first, and then to compile it into low-level machine-dependent code using a formally verified backend compiler such as the CompCert compiler, where the correct compilation of temporal operators is crucial. In this study, the formally verified compilation of Scade-like temporal operators is introduced, which is used in a formally verified compiler projects, where a Lustre-extended synchronous language is translated into the front-end intermediate language Clight in the CompCert compiler. The compilation and formal verification of temporal operators are divided into two key stages, which are implemented in the interactive proof assistant Coq.

Abstract:Crowd intelligence is a crucial component of the next generation of artificial intelligence. Researching how to stimulate and converge the innovative power of “people” in open-source communities can significantly enhance development efficiency. Community detection, as a technical approach to studying the relationships among developers in open-source projects, plays a vital role in exploring and understanding social networks. However, current research has predominantly focused on large-scale social networks such as Facebook, while systematic studies on community detection in project-level open source software developer social networks (OSS-DSN) remain limited. This study first collects real-world data and analyzes the features of OSS-DSN. Then, it benchmarks several overlapping and non-overlapping community detection algorithms on these real datasets, comparing algorithm performance across multiple metrics and dimensions. Finally, based on synthetic OSS-DSN, it generates networks efficiently and performs algorithm evaluations using ground-truth data for comparative analysis. Differences in characteristics between small- and medium-scale social networks and large-scale networks are identified, and the influence of these differences on community detection metrics and algorithm performance is explored. The study provides a new benchmark and offers important insights into communication and collaboration in open-source software communities.

Abstract:As autonomous driving applications are rapidly popularized, their safety has become the common focus of both academia and industry. Autonomous driving system (ADS) testing is an effective means for solving this problem. Currently, the mainstream testing method is the scenario-based simulation test, which evaluates the decision of ADS to be measured by simulating various elements of driving scenarios, such as roads and pedestrians. However, existing methods mainly focus on the construction and dynamic generation of critical driving scenarios, neglecting the influence of configuration changes of the vehicle itself, such as its weight and torque, on the decision-making of ADS deployed on the vehicle. To address this issue, based on the previous work SAFEVAR, this study proposes SAFEVCS, an efficient search method for safety-critical vehicle configurations. SAFEVCS employs a search algorithm to explore the vehicle configuration setting (VCS) that exposes safety vulnerabilities of ADS. Furthermore, to improve the diversity of the search results, SAFEVCS introduces fuzzing testing to optimize the conditions and constraints of crossover and mutation operators in search algorithms. To improve search efficiency, SAFEVCS further combines the vehicle dynamics knowledge, which achieves the self-adaption of search termination strategy and deduplication strategy. To evaluate the effectiveness and execution efficiency of SAFEVCS, the study takes SAFEVAR as the baseline for comparison and carries out extensive experiments under three driving scenarios. The experimental results show that VCS generated by SAFEVCS can effectively expose the safety vulnerabilities of ADS. In the two weather conditions of sunny and rainy days, under the simulation scenarios of pedestrians crossing the road, the obtained solution set significantly decreased the safety performance of the ADS under test, and under the same experiment environment, the simulation efficiency is increased by approximately 2.5 times.

Abstract:In large-scale online service systems, intricate dependencies among components often cause a single fault to trigger a massive number of correlated alerts, resulting in alert storms. Alert storms not only increase the workload of on-call engineers but also make fault diagnosis and root cause analysis more challenging. To address this issue, this study proposes Alert-CM, a graph representation learning-based alert clustering method that effectively groups alerts caused by the same fault, thereby alleviating engineers’ workloads. In alert management, an alert is typically generated by aggregating various types of underlying system data at the time of a fault, including related applications, metrics, logs, alert rules, and emergency scenarios. Alert-CM assumes that multiple alerts triggered by the same fault usually exhibit tight correlations at the underlying system data level, and that the core underlying system data better represents the abnormal system state associated with the alerts. Based on this assumption, Alert-CM constructs a fine-grained system data dependency graph using alert-related configuration data, abstracting and mapping the dependency relationships between alerts and graph nodes to further expand the alert feature space. On top of the system data dependency graph, a graph neural network model is built to perform graph representation learning, in which the contributions of core underlying system data to alerts are automatically learned, producing accurate alert vector representations. Finally, the DBSCAN algorithm is applied to cluster alerts based on the learned representations. Alert-CM is evaluated on a real-world industrial dataset, with a focus on clustering effectiveness and real-time efficiency. The experimental results demonstrate that Alert-CM significantly outperforms traditional alert aggregation methods in alert clustering tasks. Specifically, Alert-CM achieves an NMI of 0.901 and an ARI of 0.645, corresponding to average improvements of 31.7% and 153.9% over existing methods, respectively. In addition, Alert-CM exhibits strong performance in online real-time clustering tasks.

Abstract:Image denoising, a fundamental task in computer vision, relies on leveraging effective prior knowledge to restore detailed information corrupted by noise. This study proposes a feature spatial contextual Transformer for image denoising FSCformer to address the performance bottlenecks of traditional convolutional neural network (CNN) caused by fixed weights and the limitation of local receptive fields, and the high computational complexity of Transformer for global modeling. In this method, an efficient receptive field module is introduced to dynamically capture multi-scale contextual information, enhancing spatial perception while significantly reducing computational overhead. Furthermore, a convolutional attention module is adopted to integrate local feature extraction with global context modeling, improving the robustness of the model especially in complex scenes. Additionally, a cross-feature fusion mechanism is proposed to preserve image details by promoting the fine-grained interaction of multi-scale features. Extensive experiments demonstrate that the proposed method achieves a favorable trade-off between denoising accuracy and computational efficiency, outperforming several existing image denoising models across multiple benchmark datasets.

Abstract:As multimodal multiobjective optimization faces challenges of reasonably defining the individual crowdedness and dynamically balancing the decision space and objective space in individual diversity calculation, there is still significant room for performance improvement in existing multimodal multiobjective optimization algorithms. To this end, this study proposes a multimodal multiobjective differential evolution algorithm based on adaptive individual diversity (MMODE-AID). First, based on the average Euclidean distance of individuals’ nearest neighbors in the decision space or objective space, the crowdedness of individuals can be defined by multiplying the relative distances between individuals, which can more reasonably measure the true crowdedness of each individual in the corresponding space. Second, based on the overall crowdedness of the decision space and objective space, the relative crowdedness of individuals in the corresponding space is obtained, which can reasonably and dynamically balance the influence of the current state of the decision space and objective space on individual diversity calculation during the evolution process, and is conducive to the sufficient search of each equivalent Pareto optimal solution set. By employing differential evolution as the basic optimization framework, MMODE-AID evaluates individual fitness based on adaptive individual diversity. Meanwhile, it can obtain a population with excellent performance in decision space distribution, objective space distribution and convergence during offspring generation and environmental selection. MMODE-AID is compared with seven advanced multimodal multiobjective optimization algorithms on 39 benchmark test problems and one real-world application problem to validate the algorithm’s performance. The experimental results demonstrate that MMODE-AID exhibits significant competitive advantages in solving multimodal multiobjective optimization problems. The source code and original experimental data of MMODE-AID are publicly available on GitHub: https://github.com/CIA-SZU/ZQ.

Abstract:Federated learning enables numerous clients to collaboratively train a model using their local data without exposing the raw data of individual parties, thereby avoiding data leakage and misuse caused by data migration in traditional machine learning paradigms. However, in practical scenarios, clients often exhibit heterogeneous data distributions and diverse system capabilities, which degrade model performance and training efficiency. Selecting a high-quality subset of clients as participants in federated learning can effectively improve global model performance and accelerate convergence. Nevertheless, existing studies show that malicious adversaries can exploit information such as local training losses or gradients to infer sensitive private data, while current participant selection strategies for heterogeneous federated learning fail to adequately address such privacy leakage risks. To tackle this challenge, this study designs a privacy-preserving participant selection protocol for heterogeneous federated learning based on secure multi-party computation. By leveraging three-party computation (3PC) secret-sharing techniques, the proposed protocol ensures data privacy during training while maintaining the accuracy of the jointly trained model. Furthermore, a secure top-k search protocol is introduced to prevent privacy leakage during the participant selection phase. The security of the proposed protocol is formally analyzed, demonstrating that the required security properties are satisfied. Experimental results indicate that, compared with heterogeneous federated learning schemes without privacy preservation, the proposed approach increases the average computational and communication overhead across all parties by 2.09%.

Abstract:Hybrid transactional/analytical processing (HTAP) databases are capable of simultaneously supporting OLTP and OLAP workloads within a set of systems. The workload identification is a critical entry point for routing distribution in query execution. The only way to reasonably optimize the queries and allocate resources is to accurately identify whether a query belongs to OLTP or OLAP. Therefore, accurate identification of workload types is a key factor in the performance of HTAP databases. However, existing workload identification methods are mainly based on rules and cost-based measures in SQL statements, as well as machine learning approaches to differentiate workloads. These methods do not consider the inherent characteristics of query statements and utilize structural information in execution plans, resulting in low workload identification accuracy. To improve workload identification accuracy, this study proposes an intelligent method for identifying OLTP and OLAP workloads. This method extracts and encodes features from SQL statements and execution plans, builds the SQL statement encoder based on BERT, and combines the convolutional neural networks and attention mechanisms to construct the encoder of execution plans, with two types of features integrated to build a classifier. The model enables intelligent identification of workloads in HTAP hybrid workloads. Experimental verification shows that the proposed model can accurately identify OLTP and OLAP workloads with high identification accuracy. Additionally, the robustness of the model has been validated across multiple datasets, and the model is integrated into the TiDB database to verify its performance improvement on the database.

Abstract:Federated learning is currently the most advanced technology in secure multi-party machine learning and has attracted significant attention for its ability to enable collaborative model training across multiple nodes without requiring data to leave local devices. However, in real-world scenarios, client data are often non-independent and identically distributed (Non-IID), which significantly degrades the performance of the global model. Current mainstream methods primarily focus on correcting model parameter biases during training, but their effectiveness diminishes as data distribution becomes more extreme. Another category of methods aims to correct data distribution biases before local training, but this approach poses privacy risks. This study proposes a framework that adheres to strict federated learning privacy protection requirements and utilizes techniques such as differential privacy and secure multi-party computation. Assuming that client data distributions remain black boxes, the most beneficial labels for improving global model performance are selected. High-quality synthetic data are generated for these labels and distributed to clients, thus making the local data distribution closer to IID and significantly enhancing the performance of the global model. Specifically, a privacy-preserving algorithm is first designed to capture the distribution of labels across clients, and clients are grouped according to these label distribution characteristics. Then, the most worthwhile labels for generation are selected, and within the corresponding groups, clients are coordinated to collaboratively train high-quality global generative models, which are stored on the server. During the training phase of the task model, based on label distribution characteristics, samples are selectively synthesized using these generative models and distributed to clients, resulting in a more uniform local data distribution. This process reduces local model disparities and yields a high-quality global model after aggregation. Experimental results demonstrate that the proposed method can effectively improve the accuracy of the global model on the test set and reduce the number of federated learning communication rounds required before convergence. Its effectiveness surpasses that of baseline methods and has been validated on different datasets.

Abstract:Access control technology is a security mechanism for managing users’ access to resources, which can effectively prevent unauthorized access and resource leakage. In the digital age, how to balance the relationship between information circulation and privacy protection via effective access control technology and ensure the safe and orderly flow of data elements has become a problem to be urgently addressed at present. However, the existing access control technology still has problems such as insufficient integration with trust evaluation, lack of dynamic adjustment capabilities, and difficulty in precise authorization in the research on domain data sharing scenarios. To this end, a trustworthy dynamic access control model scheme based on game theory is proposed, which integrates a three-layer collaborative mechanism of “trustworthy evaluation, dynamic adjustment, and access decision”. Firstly, based on the attribute weight algorithm, a multi-factor trustworthy prediction model is designed to calculate the trust probability of the access subject. Secondly, from the perspective of long-term stability, an evolutionary game dynamic adjustment model between the access subject and the object is built to periodically and dynamically adjust the reward and punishment incentive mechanism and access authorization threshold, thereby achieving the adaptive optimization of access control. Finally, based on Bayesian game theory, an incomplete information real-time decision-making model is built, and access control decisions are made based on the mixed strategy Nash equilibrium, with the trust degree updated by the equilibrium state feedback. The results of simulation experiments and sensitivity analysis verify that the proposed scheme can effectively improve the access control accuracy and achieve dynamic adjustment of access control strategies and accurate authorization.