检索结果-内蒙古大学图书馆

Lingual-Fusion Adapter-Based Transfer Learning for Low-Resource Code Vulnerability Detection

IEEE Transactions on Consumer Electronics 2025年第1期71卷 1008-1023页

作者： Long, Xinyue Guo, Shikai Chai, Yu Li, Hui Jan, Sumaira Ameer Ma, Qian Ning, Qiao Dalian Maritime University School of Informafion Science and Technology Dalian China Key Laboratory of Artificial Intelligence of Dalian Dalian China Shanghai Jiao Tong University Shanghai China Dalian Maritime University School of Information and Science Technology Dalian China

Software vulnerabilities pose significant security threats to modern systems, particularly those involving complex execution sequences and intricate call relationships across multiple execution *** instance, in a scenario where a software system integrates legacy code in a low-resource programming language like PHP, detecting vulnerabilities becomes challenging due to data scarcity and the complexity of temporal relationships among code fragments. This scarcity hampers the ability to capture critical temporal features essential for identifying vulnerabilities spanning multiple execution ***, existing approaches face major limitations, including neglecting temporal information in code fragments and lacking sufficient data to enable effective generalization for models in low-resource *** address these challenges, we introduce, a novel approach that enhances vulnerability detection in low-resource languages by extracting complex temporal features from code fragments and employing parameter-efficient transfer learning to leverage shared knowledge from resource-rich languages. comprises two key components: 1) Code Vulnerability Detection Component: This component models temporal dependencies by leveraging execution paths extracted from Abstract Syntax Trees (ASTs), capturing both short-term variations and long-term dependencies among code fragments. This enables comprehensive extraction of complex temporal features, significantly enhancing the accuracy of vulnerability detection. 2) Cross-Lingual Transfer Component: This component learns generalizable features from resource-rich languages and efficiently transfers them to low-resource languages. By updating a small number of downstream parameters, it enhances model generalization and achieves precise vulnerability detection. We evaluated using a diverse set of programming languages from publicly available GitHub repositories, employing C as the resource-rich source language and Java, Pytho

关键词： C (programming language)

来源：评论

学校读者我要写书评

暂无评论

Badminton Action Recognition based on Improved I3D Convolutional Neural Network 3

Badminton Action Recognition based on Improved I3D Convoluti...

引用

3rd International Conference on artificial intelligence, Automation, and High-Performance Computing, AIAHPC 2023

作者： Zheng, Huangnan Shen, Huichang Zhang, Yisong Wang, Haotian School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan430063 China

ISBN: (数字)9781510666580

ISBN: (纸本)9781510666573

In order to solve the issue of inaccurate recognition of time series of badminton action by 2D networks and the high cost of using skeleton data for badminton action recognition, this article aims to explore the use of RVM (Robust Video Matting) to extract the silhouette of individuals in videos, combined with an improved I3D network (referred to as the SI3D network) for action classification in badminton matches. We collected a dataset of badminton match videos featuring multiple players and labeled them according to different action categories. By using the SI3D network for training, this article achieved good performance on the test set, with an accuracy of 91.5%. This study demonstrates the effectiveness of the I3D network in badminton action classification and provides a new research direction for action recognition in sports. © 2023 SPIE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

KSGTN-DDI: Key Substructure-aware Graph Transformer Network for Drug-drug Interaction Prediction

KSGTN-DDI: Key Substructure-aware Graph Transformer Network ...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Zhang, Peiliang Liu, Yuanjie Shen, Zhishu Wuhan University of Technology School of Computer Science and Artificial Intelligence Wuhan430070 China

ISBN: (纸本)9798350337488

Drug substructure plays a crucial role in predicting drug-drug interaction (DDI) with combination drugs for disease therapies. In order to exploit the effect of drug substructure on DDI prediction, we propose a Key Substructure-aware Graph Transformer Network for Drug-drug Interaction Prediction (KSGTN-DDI). First, the substructure-adaptive graph Transformer module adaptively explicit encoding of drug structures information. Then, the key substructure-aware module calculates the importance of different substructures in DDI prediction. Finally, the calculated important substructure aggregation features are used to reconstruct the drug-drug interactions. Relevant experiments indicate that the performance of KSGTN-DDI outperforms other DDI prediction models. © 2023 IEEE.

关键词： DDI Drug Structures Graph Neural Networks Self-attention Transformer

来源：评论

学校读者我要写书评

暂无评论

Visible and near-infrared image fusion based on information complementarity

引用

CAAI Transactions on intelligence technology 2025年第1期10卷 193-206页

作者： Zhuo Li Shiliang Pu Mengqi Ji Feng Zeng Bo Li The School of Computer Science and Engineering Beihang UniversityBeijingChina Hangzhou Hikvision Digital Technology Co. Ltd.HangzhouChina The School of Artificial Intelligence Beihang UniversityBeijingChina Hangzhou International Innovation Institute Beihang UniversityHangzhouChina

Images with complementary spectral information can be recorded using image sensors that can identify visible and near-infrared *** fusion of visible and nearinfrared(NIR)aims to enhance the quality of images acquired by video monitoring systems for the ease of user observation and data ***,current fusion algorithms produce artefacts and colour distortion since they cannot make use of spectrum properties and are lacking in information ***,an information complementarity fusion(ICF)model is designed based on physical *** order to separate high-frequency noise from important information in distinct frequency layers,the authors first extracted texture-scale and edge-scale layers using a two-scale ***,the difference map between visible and near-infrared was filtered using the extended-DoG filter to produce the initial visible-NIR complementary weight ***,to generate a guide map,the near-infrared image with night adjustment was processed as *** final complementarity weight map was subsequently derived via an arctanI function mapping using the guide map and the initial weight ***,fusion images were generated with the complementarity weight *** experimental results demonstrate that the proposed approach outperforms the state-of-the-art in both avoiding artificial colours as well as effectively utilising information complementarity.

关键词： color distortion image fusion information complementarity low light near-infrared

来源：评论

学校读者我要写书评

暂无评论

Inconsistency Detecting and Resolving for Security Policy and IPv6 Firewall Policy 7

Inconsistency Detecting and Resolving for Security Policy an...

引用

7th International Conference on computer science and artificial intelligence, CSAI 2023

作者： Yin, Yi Tateiwa, Yuichiro Qian, Xiaojun Gao, Qian Shen, Lingling Zhang, Guoqiang School of Computer and Electronic Information School of Artificial Intelligence Nanjing Normal University Nanjing China Department of Computer Science and Engineering Nagoya Institute of Technology Nagoya Japan School of Information and Technology School of Computer Science and Technology School of Artificial Intelligence Hainan Normal University Hainan China

ISBN: (纸本)9798400708688

Firewall is the first defense line for network security. Packet filtering is a basic function in firewall, it filter network packets according to a series of rules, which is called firewall policy. The design of firewall policy should be observe the regulations of security policy, which is a generic guideline that lists the basic requirements for network access permissions. However, even for IPv4 firewall policy, it is extremely hard to keep the consistency between firewall policy and security policy. Some inconsistency decision methods of security policy and IPv4 firewall policy were proposed. However, the address space of IPv6 address is a very large, the existing inconsistency decision methods could not be directly used to handle IPv6 firewall policy. To resolve the above problem, in this work, we use a formal technique to find and eliminate the inconsistencies between security policy and IPv6 firewall policy. We also build a prototype system and test the effectiveness of the proposed method through experiments. © 2023 ACM.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Convolutional Acceleration Algorithm Combining Loop Optimization and Automatic Scheduling 2

Convolutional Acceleration Algorithm Combining Loop Optimiza...

引用

2nd International Conference for Advancement in technology, ICONAT 2023

作者： Liu, Hongkang Deng, Feifei Wuhan University of Technology School of Computer Science and Artificial Intelligence Hubei Wuhan China

ISBN: (纸本)9781665475174

Convolutional neural networks are widely used in deep learning, and convolutional computation accounts for the largest proportion of time in convolutional neural networks, which basically determines the performance of the whole network, so it is important to perform acceleration optimization for the convolutional layer, which can improve the operation speed of the whole neural network to a certain extent and thus accelerate the forward inference of the model. In this paper, we propose an effective convolutional acceleration method that combines traditional compilation techniques and deep learning compilation techniques, starting from the data layout and computational order of the input matrix for convolutional operations. First, we combine the data layout of the input matrix in the MEC algorithm with the loop unrolling, which enhances the parallelism of data transformation. Next, we integrate the intermediate state matrix multiplication operation with the traditional compilation optimization technique and the Ansor [22] in deep learning compiler TVM, which effectively improves the speed of the matrix multiplication operation. In addition, our experiments show that our method effectively speeds up the convolution operation and reduces the running time. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Image Tampering Detection With Frequency-Aware Attention and Multiview Fusion

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on artificial intelligence 2025年第3期6卷 614-625页

作者： Xu, Xu Chen, Junxin Lv, Wenrui Wang, Wei Zhang, Yushu Dalian University of Technology School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Shenzhen MSU-BIT University Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Artificial Intelligence Research Institute Shenzhen518172 China Jiangxi University of Finance and Economics School of Computing and Artificial Intelligence Nanchang330013 China

Manipulated images are flooding our daily lives, which poses a threat to social security. Recently, many studies have focused on image tampering detection. However, they have poor performance on independent validation due to differences in image scenes and tampering methods. The key question is how to design a network that is able to adaptively enhance the tampering information and suppress the generalization features during training. To this end, we propose a dual-branch network with a frequency adaptation paradigm and a feature fusion module for robust tampering image detection. First, this paradigm is designed to adaptively highlight tampering features through frequency conversion and learnable weight. Second, a feature fusion module is developed to filter redundant features and dynamically fuse two-branch features. Experiments on eight typical datasets demonstrate that our model has advantages over state-of-the-art algorithms, and our paradigm can well empower semantic segmentation networks for tampering detection. © 2024 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Repeatable adaptive keypoint detection via self-supervised learning

引用

science China(Information sciences) 2022年第11期65卷 123-147页

作者： Pei YAN Yihua TAN Yuan TAI National Key Laboratory of Science & Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology

Keypoint-based matching is a fundamental technology for different computer vision tasks, in which keypoint detection is a crucial step and directly affects the entire performance. Based on deep learning approaches, the learning-based keypoint detectors have been significantly developed. To further improve the accuracy of high-level matching tasks, the extracted keypoints should provide more accurate point-to-point correspondences and maintain a uniform spatial distribution. Based on this idea, a self-supervised learning method of keypoint detection named repeatable adaptive point is proposed. This method consists of a selfsupervised objective and an optimization algorithm. The objective maximizes the repeatability measure with the sparsity constraint of keypoints. This sparsity constraint is formulated by combining the non-maximum suppression operation and the penalty function of keypoint number, which generally makes keypoints have a uniform spatial distribution. A novel approximate alternate optimization algorithm is proposed to maximize the above objective, whose convergence is proved in theory. The proposed detector is “adaptive” because the combinations of it and some existing descriptors can adapt to high-level matching tasks with a fast convergence speed. Specifically, the combinations of it and SuperPoint/HardNet descriptors achieve stateof-the-art accuracy on three high-level tasks based on image matching, namely homography estimation,camera pose estimation, and three-dimensional reconstruction. Furthermore, the proposed method converges faster on new scenes compared with the state-of-the-art method that jointly optimizes the detector and the descriptor.

关键词： keypoint detection convolutional neural network image matching self-supervised learning repeatable

来源：评论

学校读者我要写书评

暂无评论

Joint computation offloading and parallel scheduling to maximize delay-guarantee in cooperative MEC systems

引用

Digital Communications and Networks 2024年第3期10卷 693-705页

作者： Mian Guo Mithun Mukherjee Jaime Lloret Lei Li Quansheng Guan Fei Ji School of Electronics and Information Guangdong Polytechnic Normal UniversityGuangzhouChina School of Artificial Intelligence Nanjing University of Information Science and TechnologyNanjingChina Universitat Politecnica de Valencia 46022ValenciaSpain South China University of Technology China

The growing development of the Internet of Things(IoT)is accelerating the emergence and growth of new IoT services and applications,which will result in massive amounts of data being generated,transmitted and pro-cessed in wireless communication *** Edge Computing(MEC)is a desired paradigm to timely process the data from IoT for value *** MEC,a number of computing-capable devices are deployed at the network edge near data sources to support edge computing,such that the long network transmission delay in cloud computing paradigm could be *** an edge device might not always have sufficient resources to process the massive amount of data,computation offloading is significantly important considering the coop-eration among edge ***,the dynamic traffic characteristics and heterogeneous computing capa-bilities of edge devices challenge the *** addition,different scheduling schemes might provide different computation delays to the offloaded ***,offloading in mobile nodes and scheduling in the MEC server are coupled to determine service *** paper seeks to guarantee low delay for computation intensive applica-tions by jointly optimizing the offloading and scheduling in such an MEC *** propose a Delay-Greedy Computation Offloading(DGCO)algorithm to make offloading decisions for new tasks in distributed computing-enabled mobile devices.A Reinforcement Learning-based Parallel Scheduling(RLPS)algorithm is further designed to schedule offloaded tasks in the multi-core MEC *** an offloading delay broadcast mechanism,the DGCO and RLPS cooperate to achieve the goal of delay-guarantee-ratio ***,the simulation results show that our proposal can bound the end-to-end delay of various *** under slightly heavy task load,the delay-guarantee-ratio given by DGCO-RLPS can still approximate 95%,while that given by benchmarked algorithms is reduced to intolerable *** simulation resul

关键词： Edge computing Computation offloading Parallel scheduling Mobile-edge cooperation Delay guarantee

来源：评论

学校读者我要写书评

暂无评论

Cyclical Training Framework with Graph Feature Optimization for Knowledge Graph Reasoning

引用

computers, Materials & Continua 2025年第5期83卷 1951-1971页

作者： Xiaotong Han Yunqi Jiang Haitao Wang Yuan Tian School of Artificial Intelligence Jilin UniversityChangchun130012China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence MOEChangchun130012China College of Computer Science and Technology Jilin UniversityChangchun130012China

Knowledge graphs(KGs),which organize real-world knowledge in triples,often suffer from issues of *** address this,multi-hop knowledge graph reasoning(KGR)methods have been proposed for interpretable knowledge graph *** primary approaches to KGR can be broadly classified into two categories:reinforcement learning(RL)-based methods and sequence-to-sequence(seq2seq)-based *** each method has its own distinct advantages,they also come with inherent *** leverage the strengths of each method while addressing their weaknesses,we propose a cyclical training method that alternates for several loops between the seq2seq training phase and the policy-based RL training phase using a transformer ***,a multimodal data encoding(MDE)module is introduced to improve the representation of entities and relations in *** module treats entities and relations as distinct modalities,processing each with a dedicated network specialized for its respective *** then combines the representations of entities and relations in a dynamic and fine-grained manner using a gating *** experimental results from the knowledge graph completion task highlight the effectiveness of the proposed *** five benchmark datasets,our framework achieves an average improvement of 1.7%in the Hits@1 metric and a 0.8%average increase in the Mean Reciprocal Rank(MRR)compared to other strong baseline ***,the maximum improvement in Hits@1 exceeds 4%,further demonstrating the effectiveness of the proposed approach.

关键词： Knowledge graph reinforcement learning transformer

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：