检索结果-内蒙古大学图书馆

A reinforcement learning malware detection model based on heterogeneous information network path representation

APPLIED INTELLIGENCE 2025年第6期55卷 1-18页

作者： Yang, Kang Cai, Lizhi Wu, Jianhua Liu, Zhenyu Zhang, Meng Shanghai Key Lab Comp Software Testing & Evaluatin Shanghai 201112 Peoples R China Shanghai Dev Ctr Comp Software Technol Shanghai 201112 Peoples R China

With the significant increase of Android malware, the APP privacy data leakage incidents occur frequently, which poses a great threat to user property and information security. Specifically, the new malware has the characteristics of high evolution rate and diverse variants, leading to the fact that the current malware detection methods still have three key problems: (1) Difficulty in acquiring Android sample structural features;(2) Weakly in representing malware behavior structure;(3) Poor robustness of the detection model. To address the above limitations, we propose a new malware detection framework MPRLDroid with reinforcement learning. First of all, the MPRLDroid model extracts the Android APP structural features and constructs the heterogeneous information network data based on the semantic call structure between APP, API and permission. Subsequently, the model utilizes reinforcement learning to adaptively generate a meta-path for each sample and combines it with a graph attention network to effectively represent the graph of nodes. Finally, the low-dimensional graph node vector data is brought into the downstream detection task for classification, where the performance change of the classification result is used as a reward function for reinforcement learning. The experimental results demonstrate that the MPRLDroid model, when integrated with reinforcement learning, outperforms the baseline models in terms of performance, and its detection model exhibits greater robustness compared to other models.

关键词： Android Malware detection Reinforcement learning Feature representation

来源：评论

学校读者我要写书评

暂无评论

Automatic Code Summarization Using Abbreviation Expansion and Subword Segmentation

引用

EXPERT SYSTEMS 2025年第2期42卷

作者： Liang, Yu-Guo Fan, Gui-Sheng Yu, Hui-Qun Li, Ming-Chen Huang, Zi-Jie East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai Peoples R China Shanghai Dev Ctr Comp Software Technol Shanghai Key Lab Comp Software Testing & Evaluatin Shanghai Peoples R China

Automatic code summarization refers to generating concise natural language descriptions for code snippets. It is vital for improving the efficiency of program understanding among software developers and maintainers. Despite the impressive strides made by deep learning-based methods, limitations still exist in their ability to understand and model semantic information due to the unique nature of programming languages. We propose two methods to boost code summarization models: context-based abbreviation expansion and unigram language model-based subword segmentation. We use heuristics to expand abbreviations within identifiers, reducing semantic ambiguity and improving the language alignment of code summarization models. Furthermore, we leverage subword segmentation to tokenize code into finer subword sequences, providing more semantic information during training and inference, thereby enhancing program understanding. These methods are model-agnostic and can be readily integrated into existing automatic code summarization approaches. Experiments conducted on two widely used Java code summarization datasets demonstrated the effectiveness of our approach. Specifically, by fusing original and modified code representations into the Transformer model, our Semantic Enhanced Transformer for Code Summarizsation (SETCS) serves as a robust semantic-level baseline. By simply modifying the datasets, our methods achieved performance improvements of up to 7.3%, 10.0%, 6.7%, and 3.2% for representative code summarization models in terms of BLEU-4, METEOR, ROUGE-L and SIDE, respectively.

关键词： automatic code summarization code abbreviation expansion deep learning program understanding subword segmentation

来源：评论

学校读者我要写书评

暂无评论

AccMILP: An Approach for Accelerating Neural Network Verification Based on Neuron Importance 28th

AccMILP: An Approach for Accelerating Neural Network Verific...

引用

28th International Conference on Engineering of complex computer Systems (ICECCS)

作者： Zheng, Fei Xu, Qingguo Lei, Zhou Miao, Huaikou Shanghai Univ Sch Comp Engn & Sci Shanghai Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9783031664557;9783031664564

Deep Neural Networks (DNNs) have found successful applications in various non-safety-critical domains. However, given the inherent lack of interpretability in DNNs, ensuring their prediction accuracy through robustness verification becomes imperative before deploying them in safety-critical applications. Neural Network Verification (NNV) approaches can broadly be categorized into exact and approximate solutions. Exact solutions are complete but time-consuming, making them unsuitable for large network architectures. In contrast, approximate solutions, aided by abstraction techniques, can handle larger networks, although they may be incomplete. This paper introduces AccMILP, an approach that leverages abstraction to transform NNV problems into Mixed Integer Linear Programming (MILP) problems. AccMILP considers the impact of individual neurons on target labels in DNNs and combines various relaxation methods to reduce the size of NNV models while ensuring verification accuracy. The experimental results indicate that AccMILP can reduce the size of the verification model by approximately 30% and decrease the solution time by at least 80% while maintaining performance equal to or greater than 60% of MIPVerify. In other words, AccMILP is well-suited for the verification of large-scale DNNs.

关键词： Neural network Formal verification Mixed integer linear programming Neuron importance

来源：评论

学校读者我要写书评

暂无评论

A review on multi-focus image fusion using deep learning

引用

NEUROcompUTING 2025年 618卷

作者： Luo, Fei Zhao, Baojun Fuentes, Joel Zhang, Xueqin Ding, Weichao Gu, Chunhua Pino, Luis Rojas East China Univ Sci & Technol Sch Informat Sci & Engn Shanghai 200237 Peoples R China Shanghai Dev Ctr Comp Software Technol Shanghai Key Lab Comp Software Evaluating & Testin Shanghai 201203 Peoples R China Univ Bio Bio Dept Comp Sci & Informat Technol Chillan 3780000 Chile Univ San Sebastian Sch Engn Architecture & Design Santiago 8320000 Chile

Multi-focus image fusion (MFIF) is an image enhancement technique that investigates how to obtain a fully focused image from multiple defocus images, providing fundamental services for computer vision fields, such as image recognition, 3D reconstruction, medical diagnosis, computational photography, etc. In recent years, the deep learning-based MFIF has broken through the limitations of traditional MFIF and achieved superior fusion results. Existing reviews on MFIF mainly classify and describe the techniques at the technical level, such as supervised/unsupervised learning methods and network types, but lack discussion and analysis on problem scenarios. Therefore, based on the problem scenarios of MFIF, this paper categorizes deep learning-based MFIF research into six types: MFIF with lightweight networks, MFIF for artifacts and defocus spread effects, MFIF for information preservation, MFIF with unified fusion networks, MFIF on addressing suboptimal initial decision map and MFIF in challenging environments. Furthermore, this paper summarizes commonly used synthesis datasets and real datasets for MFIF, and statistically describes the main evaluation metrics. Finally, this paper analyzes the shortcomings of existing algorithms, and identifies potential future research directions, aiming to provide objective reviews for MFIF researchers focusing on different problem scenarios.

关键词： Image enhancement technique MFIF Deep learning Most-frequently-used datasets Statistics about evaluation metrics

来源：评论

学校读者我要写书评

暂无评论

Improving Retrieval-Augmented Deep Assertion Generation via Joint Training

引用

IEEE TRANSACTIONS ON software ENGINEERING 2025年第4期51卷 1232-1247页

作者： Zhang, Quanjun Fang, Chunrong Zheng, Yi Qian, Ruixiang Yu, Shengcheng Zhao, Yuan Zhou, Jianyi Yang, Yun Zheng, Tao Chen, Zhenyu Nanjing Univ State Key Lab Novel Software Technol Nanjing 210093 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testin Shanghai 201112 Peoples R China Huawei Cloud Comp Technol Co Ltd Beijing 100094 Peoples R China Swinburne Univ Technol Dept Comp Technol Melbourne Vic 3122 Australia Nanjing Univ Shenzhen Res Inst Nanjing 210093 Peoples R China

Unit testing attempts to validate the correctness of basic units of the software system under test and has a crucial role in software development and testing. However, testing experts have to spend a huge amount of effort to write unit test cases manually. Very recent work proposes a retrieve-and-edit approach to automatically generate unit test oracles, i.e., assertions. Despite being promising, it is still far from perfect due to some limitations, such as splitting assertion retrieval and generation into two separate components without benefiting each other. In this paper, we propose AG-RAG, a retrieval-augmented automated assertion generation (AG) approach that leverages external codebases and joint training to address various technical limitations of prior work. Inspired by the plastic surgery hypothesis, AG-RAG attempts to combine relevant unit tests and advanced pre-trained language models (PLMs) with retrieval-augmented fine-tuning. The key insight of AG-RAG is to simultaneously optimize the retriever and the generator as a whole pipeline with a joint training strategy, enabling them to learn from each other. Particularly, AG-RAG builds a dense retriever to search for relevant test-assert pairs (TAPs) with semantic matching and a retrieval-augmented generator to synthesize accurate assertions with the focal-test and retrieved TAPs as input. Besides, AG-RAG leverages a code-aware language model CodeT5 as the cornerstone to facilitate both assertion retrieval and generation tasks. Furthermore, AG-RAG designs a joint training strategy that allows the retriever to learn from the feedback provided by the generator. This unified design fully adapts both components specifically for retrieving more useful TAPs, thereby generating accurate assertions. AG-RAG is a generic framework that can be adapted to various off-the-shelf PLMs. We extensively evaluate AG-RAG against six state-of-the-art AG approaches on two benchmarks and three metrics. Experimental results show th

关键词： Generators Training Codes testing Accuracy Semantics Pipelines Test pattern generators Surgery Benchmark testing Unit testing assertion generation pre-trained language models AI4SE

来源：评论

学校读者我要写书评

暂无评论

The Web Application Test Based on Page Coverage Criteria

引用

Journal of Donghua University(English Edition) 2008年第3期25卷 291-296页

作者：蔡立志童维勤杨根兴 School of Computer Engineering and Science Shanghai University The Key Lab of Software Testing and Evaluating

software testing coverage criteria play an important role in the whole testing *** current coverage criteria for web applications are based on program or *** are not suitable for black-box test or intuitional to *** paper defines a kind of test criteria based on page coverage sequences only navigated by web application,including Page_Single,Page_Post,Page_Pre,Page_Seq2,Page_*** test criteria based on page coverage sequences made by interactions between web application and browser are being under consideration after *** order to avoid ambiguity of natural language,these coverage criteria are depicted using Z formal *** empirical result shows that the criteria complement traditional coverage and fault detection capability criteria.

关键词： web application coverage criteria browser interaction Z formal language

来源：评论

学校读者我要写书评

暂无评论

An overlapping network community partition algorithm based on semi-supervised matrix factorization and random walk

引用

EXPERT SYSTEMS WITH APPLICATIONS 2018年 91卷 277-285页

作者： Li, Weimin Xie, Jun Xin, Mingjun Mo, Jun Shanghai Univ Sch Comp Engn & Technol Shanghai Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

The discovery of community structure is the basis of understanding the topology structure and social function of the network. It is also an important factor for recommendation technology, information dissemination, event prediction, and more. In this paper, we consider the structure and characteristics of the social network and propose an algorithm based on semi-supervised matrix factorization and random walk. The proposed method first calculates the transition probability between nodes through the topology of the network. The random walk model is then used to obtain the final walk probability, and the feature matrix is constructed. At the same time, we combine a priori content information in the network to build a must-link matrix and a cannot-link matrix. We then merge them into the feature matrix of the random walk to form a new feature matrix. Finally, the expectation of the number of edges is defined according to the factorized membership matrix. Results demonstrate the effectiveness and better performance of our method. (C) 2017 Elsevier Ltd. All rights reserved.

关键词： Matrix factorization Random walk Node convergence degree Node influence

来源：评论

学校读者我要写书评

暂无评论

SDMS-O: A service deployment management system for optimization in clouds while guaranteeing users' QoS requirements

引用

FUTURE GENERATION compUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE 2012年第7期28卷 1100-1109页

作者： Liu, Tiejiang Lu, Tun Wang, Wei Wang, Qi Liu, Zhenyu Gu, Ning Ding, Xianghua Fudan Univ Sch Comp Sci Shanghai 200433 Peoples R China Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

In a service oriented cloud, in order to meet users' functional and non-functional requirements, cloud vendors must manage service deployment effectively. During the deployment process, the cost of deployment and its influence on the cloud are very important issues to consider;however, so far little research has been done to address them. In this paper, we present a Service Deployment Management System for Optimization (SDMS-O) designed with a novel optimization approach for service deployment to improve deployment efficiency and reduce deployment cost while guaranteeing the users' QoS requirements. In SDMS-O, atom-services as its basic units of service applications are first divided into different service families according to compatibility and installation policy, and a service deployment requirement is expressed as an installation expression sequence. We then present three algorithms to automatically standardize, simplify and optimize this sequence during the service deployment process. Meanwhile, the backtracking technique is applied in each optimization phase of service deployment in order not to violate the users' QoS constraints. The service deployment result such as safety and usability in each optimization step is also evaluated. A simulated experiment of SDMS-O demonstrates our approach's effectiveness and efficiency. (C) 2011 Elsevier B.V. All rights reserved.

关键词： Cloud computing Service family Installation expression Deployment optimization QoS requirements

来源：评论

学校读者我要写书评

暂无评论

M-DETR: Multi-scale DETR for Optical Music Recognition

引用

EXPERT SYSTEMS WITH APPLICATIONS 2024年第PartB期249卷

作者： Luo, Fei Dai, Yifan Fuentes, Joel Ding, Weichao Zhang, Xueqin East China Univ Sci & Technol Shanghai Peoples R China Univ Bio Bio Dept Comp Sci & Informat Technol Chillan 3780000 Chile Shanghai Key Lab Comp Software Evaluating Testing Shanghai Peoples R China

Optical Music Recognition (OMR) is an important way to digitize score images and has broad application prospects in fields such as the storage of music documents, music education and digital creation. As a new paradigm for object detection, DETR (detection transformer) has the ability to associate contextual information, which can be exploited to resolve the OMR task. However, the original DETR does not fit OMR well due to its high computational complexity and numerous parameters. To address the DETR defects and improve the recognition accuracy of OMR, we propose a novel multi-scale DETR (M-DETR) with a multi-scale feature fusion mechanism and improved attention mechanisms. First, a new multi-scale feature fusion mechanism is designed to let the backbone network of M-DETR get rich multi-scale information. Then, a key-region attention mechanism is incorporated based on the character that the key information is concentrated on a score image. Finally, the pre-context attention mechanism is introduced to make better use of the contextual association between recognition notes in music scores. Experiment results show that M-DETR achieves recognition accuracy of 90.6% for 7 typical small-sized notes, which is better than Faster R-CNN and YOLO v5, and the improvement rate is 10.02% compared to the original DETR algorithm. The results indicate that M-DETR is an effective way for the OMR task, which also provides a new solution for the detection of small-sized objects with contextual association.

关键词： OMR DETR Feature fusion Attention mechanism

来源：评论

学校读者我要写书评

暂无评论

A Maintainability Spreadsheet-Driven Regression Test Automation Framework

A Maintainability Spreadsheet-Driven Regression Test Automat...

引用

IEEE 16th International Conference on computational Science and Engineering (CSE)

作者： Liu, Zhenyu Chen, Qiang Jiang, Xu Shanghai Key Lab Comp Software Evaluating & Testi Shanghai Peoples R China

ISBN: (纸本)9781479948970

complete browser-based software is need to develop a separate complicated script or some scripts with existing automation testing tools. The paper proposed a regression test automation framework to implement automation test without script development during the test development. The form, data and control spreadsheet should be defined by test developer. The test automation framework provided a series of function interface to accomplish test execution. The definition spreadsheet is easy to maintain in novel framework. In regression test, testers merely need to modify the related definition in spreadsheet. The detailed case is given used with framework and support by mainstream automation test tool.

关键词： software test Regression test Automation test Test framework

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：