检索结果-内蒙古大学图书馆

APT-KGL: An Intelligent APT Detection System Based on Threat Knowledge and Heterogeneous Provenance Graph Learning

IEEE Transactions on Dependable and Secure Computing 2022年 1-15页

作者： Chen, Tieming Dong, Chengyu Lv, Mingqi Song, Qijie Liu, Haiwen Zhu, Tiantian Xu, Kang Chen, Ling Ji, Shouling Fan, Yuan College of Computer Science and Technology Zhejiang University of Technology Hangzhou China College of Computer Science and Technology Zhejiang University Hangzhou China DAS-Security Hangzhou China

APTs (Advanced Persistent Threats) have caused serious security threats worldwide. Most existing APT detection systems are implemented based on sophisticated forensic analysis rules. However, the design of these rules requires in-depth domain knowledge and the rules lack generalization ability. On the other hand, deep learning technique could automatically create detection model from training samples with little domain knowledge. However, due to the persistence, stealth, and diversity of APT attacks, deep learning technique suffers from a series of problems including difficulties of capturing contextual information, low scalability, dynamic evolving of training samples, and scarcity of training samples. Aiming at these problems, this paper proposes APT-KGL, an intelligent APT detection system based on provenance data and graph neural networks. First, APT-KGL models the system entities and their contextual information in the provenance data by a HPG (Heterogeneous Provenance Graph), and learns a semantic vector representation for each system entity in the HPG in an offline way. Then, APT-KGL performs online APT detection by sampling a small local graph from the HPG and classifying the key system entities as malicious or benign. In addition, to conquer the difficulty of collecting training samples of APT attacks, APT-KGL creates virtual APT training samples from open threat knowledge in a semi-automatic way. We conducted a series of experiments on two provenance datasets with simulated APT attacks. The experiment results show that APT-KGL outperforms other current deep learning based models, and has competitive performance against state-of-the-art rule-based APT detection systems. IEEE

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Collision-free parking recommendation based on multi-agent reinforcement learning in vehicular crowdsensing

引用

Digital Communications and Networks 2024年第3期10卷 609-619页

作者： Xin Li Xinghua Lei Xiuwen Liu Hang Xiao College of Computer Science and Technology China University of Petroleum(East China)QingDao266580China

The recent proliferation of Fifth-Generation(5G)networks and Sixth-Generation(6G)networks has given rise to Vehicular Crowd Sensing(VCS)systems which solve parking collisions by effectively incentivizing vehicle ***,instead of being an isolated module,the incentive mechanism usually interacts with other *** on this,we capture this synergy and propose a Collision-free Parking Recommendation(CPR),a novel VCS system framework that integrates an incentive mechanism,a non-cooperative VCS game,and a multi-agent reinforcement learning algorithm,to derive an optimal parking strategy in real ***,we utilize an LSTM method to predict parking areas roughly for recommendations *** incentive mechanism is designed to motivate vehicle participation by considering dynamically priced parking tasks and social network *** order to cope with stochastic parking collisions,its non-cooperative VCS game further analyzes the uncertain interactions between vehicles in parking *** its multi-agent reinforcement learning algorithm models the VCS campaign as a multi-agent Markov decision process that not only derives the optimal collision-free parking strategy for each vehicle independently,but also proves that the optimal parking strategy for each vehicle is ***,numerical results demonstrate that CPR can accomplish parking tasks at a 99.7%accuracy compared with other baselines,efficiently recommending parking spaces.

关键词： Incentive mechanism Non-cooperative VCS game Multi-agent reinforcement learning Collision-free parking strategy Vehicular crowdsensing

来源：评论

学校读者我要写书评

暂无评论

Joint DNN Partitioning and Task Offloading Based on Attention Mechanism-Aided Reinforcement Learning

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2914-2927页

作者： Zhang, Mengyuan Fang, Juan Teng, Ziyi Liu, Yaqi Wu, Shen College of Computer Science Beijing University of Technology Beijing100124 China

The rapid advancement of artificial intelligence applications has resulted in the deployment of a growing number of deep neural networks (DNNs) on mobile devices. Given the limited computational capabilities and small battery capacity of these devices, supporting efficient DNN inference presents a significant challenge. This paper considers the joint design of DNN model partitioning and offloading under high-concurrent tasks scenarios. The primary objective is to accelerate DNN task inference and reduce computational delay. Firstly, we propose an innovative adaptive inference framework that partitions DNN models into interdependent sub-tasks through a hierarchical partitioning method. Secondly, we develop a delay prediction model based on a Random Forest (RF) regression algorithm to estimate the computational delay of each sub-task on different devices. Finally, we designed a high-performance DNN partitioning and task offloading method based on an attention mechanism-aided Soft Actor-Critic (AMSAC) algorithm. The bandwidth allocation for each user is determined by the attention mechanism based on the characteristics of the DNN tasks, and the Soft Actor-Critic algorithm is used for adaptive layer-level partitioning and offloading of the DNN model, reducing collaborative inference delay. Extensive experiments demonstrate that our proposed AMSAC algorithm effectively reduces DNN task inference latency cost and improves service quality. © 2004-2012 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

ED-Ged:Nighttime Image Semantic Segmentation Based on Enhanced Detail and Bidirectional Guidance

引用

computers, Materials & Continua 2024年第8期80卷 2443-2462页

作者： Xiaoli Yuan Jianxun Zhang Xuejie Wang Zhuhong Chu College of Computer Science and Engineering Chongqing University of TechnologyChongqing400054China

Semantic segmentation of driving scene images is crucial for autonomous *** deep learning technology has significantly improved daytime image semantic segmentation,nighttime images pose challenges due to factors like poor lighting and overexposure,making it difficult to recognize small *** address this,we propose an Image Adaptive Enhancement(IAEN)module comprising a parameter predictor(Edip),multiple image processing filters(Mdif),and a Detail Processing Module(DPM).Edip combines image processing filters to predict parameters like exposure and hue,optimizing image *** adopt a novel image encoder to enhance parameter prediction accuracy by enabling Edip to handle features at different *** strengthens overlooked image details,extending the IAEN module’s *** the segmentation network,we integrate a Depth Guided Filter(DGF)to refine segmentation *** entire network is trained end-to-end,with segmentation results guiding parameter prediction optimization,promoting self-learning and network *** lightweight and efficient network architecture is particularly suitable for addressing challenges in nighttime image *** experiments validate significant performance improvements of our approach on the ACDC-night and Nightcity datasets.

关键词： Night driving semantic segmentation nighttime image processing adverse illumination differentiable filters

来源：评论

学校读者我要写书评

暂无评论

AFPN: Asymptotic Feature Pyramid Network for Object Detection

AFPN: Asymptotic Feature Pyramid Network for Object Detectio...

引用

2023 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2023

作者： Yang, Guoyu Lei, Jie Zhu, Zhikuan Cheng, Siyu Feng, Zunlei Liang, Ronghua College of Computer Science Zhejiang University of Technology Hangzhou China College of Computer Science Zhejiang University Hangzhou China

ISBN: (纸本)9798350337020

Multi-scale features are of great importance in encoding objects with scale variance in object detection tasks. A common strategy for multi-scale feature extraction is adopting the classic top-down and bottom-up feature pyramid networks. However, these approaches suffer from the loss or degradation of feature information, impairing the fusion effect of non-adjacent levels. This paper proposes an asymptotic feature pyramid network (AFPN) to support direct interaction at non-adjacent levels. AFPN is initiated by fusing two adjacent low-level features and asymptotically incorporates higher-level features into the fusion process. In this way, the larger semantic gap between non-adjacent levels can be avoided. Given the potential for multi-object information conflicts to arise during feature fusion at each spatial location, adaptive spatial fusion operation is further utilized to mitigate these inconsistencies. We incorporate the proposed AFPN into both two-stage and one-stage object detection frameworks and evaluate with the MS-COCO 2017 validation and test datasets. Experimental evaluation shows that our method achieves more competitive results than other state-of-the-art feature pyramid networks. The code is available at https://***/gyyang23/AFPN. © 2023 IEEE.

关键词： adaptive spatial fusion asymptotic fusion feature pyramid network object detection

来源：评论

学校读者我要写书评

暂无评论

Surface Defect Detection Algorithm for Strip Steel Based on Improved YOLOv7 Model

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第3期51卷 308-316页

作者： Wang, Zhu Liu, Weisheng the College of Computer Science and Software Engineering University of Science and Technology Liaoning Anshan China the College of Computer Science and Software Engineering the University of Science and Technology Liaoning CO Anshan114051 China

This research proposes a refined deep learning framework aimed at boosting the precision and efficacy of detecting surface imperfections in strip steel. This method integrates enhancement and simplification techniques inspired by the You Only Look Once version 7 (YOLOv7) detection method, resulting in significant enhancements in the model's accuracy, speed, and flexibility. The substitution of ELAN with Bottleneck Transformer 3 (BoT3) leads to improved accuracy and mean Average Precision (mAP) values, while also introducing a more lightweight network architecture. The incorporation of the Involution mechanism enhances the model's feature extraction capabilities, thereby improving its ability to recognize small targets through the utilization of local perceptual fields. The ASPP_CA architecture leverages a multi-scale feature fusion technique along with an attention mechanism to reduce model parameters and enhance inference speed. Furthermore, it extends the model's receptive field, allowing it to capture additional visual information. The enhanced algorithm, denoted as YOLOv7-IBA, demonstrates empirical results that underscore its superiority over the three current state-of-the-art detection techniques in identifying surface flaws on strip steel. The accuracy has been improved to 82.9%, representing a significant increase of 7.2% compared to the previous performance. Furthermore, the mean mAP value has experienced a 3.2% increase, reaching a total of 79.9%. Moreover, there has been a remarkable 8.8% improvement in efficiency. The adoption of this approach holds the potential to enhance both the precision and productivity of strip surface flaw detection, while also providing valuable methodological support for the advancement of other related disciplines. © (2024), (International Association of Engineers). All Rights Reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Development of selenium nanoparticles stabilized by novel polysaccharides from Stauntonia brachyanthera pulp for anti-hepatoma cell proliferation

引用

Food Bioscience 2023年第3期53卷 2803-2811页

作者： Ningxiang Yu Hui Chen Abel Wend-Soo Zongo Yuanchao Lu Xiaohua Nie Xianghe Meng College of Food Science and Technology Zhejiang University of TechnologyHangzhou310014ZhejiangChina

In this study,the novel polysaccharides extracted from Stauntonia Brachyanthera pulp were used as stabilizers for the preparation of selenium nanoparticles(SBPPs-SeNPs).The preparation process,structural characterization,stability,and anti-hepatoma cell activity of SBPPs-SeNPs were studied in *** results showed that the SBPPs-SeNPs were symmetrical spheres with an average diameter of about 30-40 nm under optimal process *** interacted with SeNPs via hydroxyl groups on the surface of SBPPs to form C-O-Se ***-SeNPs exhibited good stability during the 21-day storage period at 4℃,likely due to the interaction between SeNPs and the hydroxyl ***,in vitro anti-tumor experiments demonstrated that SBPPs-SeNPs significantly inhibited the proliferation of HepG2 cells in a dose-dependent manner,and induced morphological changes,and cell cycle arrest in S ***-SeNPs also triggered apoptosis in HepG2 cells through the mitochondrial *** findings suggested that SBPPs-SeNPs have the potential to become novel anti-hepatoma agents.

关键词： Stauntonia brachyanthera pulp polysaccharides Selenium nanoparticles Structural characterization Stability Anti-hepatoma activity

来源：评论

学校读者我要写书评

暂无评论

Scene text recognition with context-aware autonomous bidirectional iterative models

引用

Journal of Intelligent and Fuzzy Systems 2024年第4期46卷 8605-8616页

作者： Zhao, Xiaoqing Xu, Miaomiao Li, Yanbing Huang, Hao Silamu, Wushour College of Computer Science and Technology Xinjiang University Urumqi China

This research focuses on Scene Text Recognition (STR), a crucial component in various applications of artificial intelligence such as image retrieval, office automation, and intelligent traffic systems. Recent studies have shown that semantic-aware approaches significantly improve the performance of STR tasks, with context-aware STR methods becoming mainstream. Among these, the fusion of visual and language models has shown remarkable effectiveness. We propose a novel method (PABINet) that incorporates three key components: a Visual-Language Decoder, a Language Model, and a Fusion Model. First, during training, the Visual-Language Decoder masks the original labels in the Transformer decoder using permutation masks, with each mask being unique. This enhances word memorization and learning through contextual semantic information, resulting in robust semantic knowledge. During the inference stage, the Visual-Language Decoder employs autonomous Autoregressive model (AR) inference to generate results. Subsequently, the Language Model scrutinizes and corrects the output of the Visual-Language Encoder using a cloze mask approach, achieving context-aware, autonomous, bidirectional inference. Finally, the Fusion Model concatenates and refines the outputs of both models through iterative *** results demonstrate that our PABINet performs exceptionally well when handling various quality images. When trained with synthetic data, PABINet achieves a new STR benchmark (average accuracy of 92.41%), and when trained with real data, it establishes new state-of-the-art results (average accuracy of 96.28%). © 2024 – IOS Press. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Digital media design and production method based on multimedia human–computer interaction technology

引用

Discover Artificial Intelligence 2025年第1期5卷 1-14页

作者： Xu, Piwen College of Computer Science and Technology Tiangong University Tianjin300387 China

Digital media interaction design mainly focuses on the user’s interactive experience in the digital media environment. By designing interaction methods that conform to human cognition and behavioral habits, it improves the efficiency and comfort of user interaction with digital devices. Its development history can be traced back to the early stage of computers and the Internet. With the development of graphical user interfaces, mobile Internet and intelligent devices, the application scenarios of digital media interaction design are increasingly rich, and the design complexity is also increasingly high. The innovation of this article lies in combining the GOMS model with execution level quantitative optimization techniques to construct a new optimization model. This model can not only accurately describe the user’s operational behavior on digital media mobile terminals, but also quantitatively evaluate the interface’s interaction efficiency and user experience. By collecting and analyzing real-time user data during task execution, this model can optimize various aspects such as interface layout, button size, and interaction flow, thereby improving user operational efficiency and satisfaction. In terms of application in the design of digital media mobile terminal interfaces, this optimization model demonstrates significant advantages. © The Author(s) 2025.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

BTSC: Binary tree structure convolution layers for building interpretable decision-making deep CNN

引用

CAAI Transactions on Intelligence technology 2024年第5期9卷 1331-1345页

作者： Yuqi Wang Dawei Dai Da Liu Shuyin Xia Guoyin Wang College of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqingChina

Although deep convolution neural network(DCNN)has achieved great success in computer vision field,such models are considered to lack interpretability in *** of fundamental issues is that its decision mechanism is considered to be a“black-box”*** authors design the binary tree structure convolution(BTSC)module and control the activation level of particular neurons to build the interpretable DCNN ***,the authors design a BTSC module,in which each parent node generates two independent child layers,and then integrate them into a normal DCNN *** main advantages of the BTSC are as follows:1)child nodes of the different parent nodes do not interfere with each other;2)parent and child nodes can inherit ***,considering the activation level of neurons,the authors design an information coding objective to guide neural nodes to learn the particular information coding that is *** the experiments,the authors can verify that:1)the decision-making made by both the ResNet and DenseNet models can be explained well based on the"decision information flow path"(known as the decision-path)formed in the BTSC module;2)the decision-path can reasonably interpret the decision reversal mechanism(Robustness mechanism)of the DCNN model;3)the credibility of decision-making can be measured by the matching degree between the actual and expected decision-path.

关键词： deep learning deep neural networks neura1 nets pattern classification

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：