检索结果-内蒙古大学图书馆

28th International Conference on database Systems for Advanced Applications, DASFAA 2023

作者： Hu, Die Xie, Yulai Feng, Dan Zhao, Shixun Fu, Pengyu Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan China School of Cyber Science and Engineering Hubei Engineering Research Center on Big Data Security Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9783031306365

With the rapid development of mobile Internet technology, various public events appear on social media platforms and attract a lot of attention. Since netizens can express their opinions freely on the Internet, some events that cause negative public opinion seriously threaten public security, which are called Internet Public Safety events (IPSe). Existing solutions use a single metric to realize event detection, which has a high false detection rate for Internet Public Safety events. In addition, they lack countermeasures after the outbreak of public opinion, resulting in inefficient information management. This paper proposes a novel Internet Public Safety event grading method based on multi-feature, which measures events from the three perspectives of heat, emotion, and sensitivity. In order to improve the retrieval efficiency of events information, we implement a smart dynamic hot/cold data migration mechanism using a hybrid storage system containing solid-state drives and hard-disk drives, which realizes real-time data adjustment in the storage layer and ensures efficient events management. In the experiments, we verify our method through several real internet events, and the results show that our method achieves the state-of-the-art accuracy in the detection of Internet Public Safety events and realizes efficient retrieval with a low query overhead. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Grading

来源：评论

学校读者我要写书评

暂无评论

Tensor-Based Multi-Scale Correlation Anomaly Detection for AIoT-Enabled Consumer Applications

引用

IEEE Transactions on Consumer Electronics 2024年第1期71卷 2061-2071页

作者： Zeng, Jiuzhen Yang, Laurence T. Wang, Chao Deng, Xianjun Yang, Xiangli Huazhong University of Science and Technology Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Wuhan430074 China Huazhong University of Science and Technology School of Cyber Science and Engineering Wuhan430074 China Zhengzhou University School of Computer and Artificial Intelligence Zhengzhou450001 China St. Francis Xavier University Department of Computer Science AntigonishNSB2G 2W5 Canada University of South China School of Electrical Engineering Hengyang421001 China

Artificial Intelligence of Things (AIoT) is an innovative paradigm expected to enable various consumer applications that is transforming our lives. While enjoying benefits and services from these applications, we also face serious security issues due to malicious cyber attacks on the massive growth of AIoT consumer devices. Accurate anomaly detection is one of the critical tasks for the trustworthy AIoT removing those obstacles. However, limited by the vector-based data pattern and ill-considered factors for anomalous samples analysis, existing methods suffer from the low detection performance. In this paper, a multi-scale correlation tensor convolutional Gaussian mixture network (named as MTCGM) is presented for ameliorating this actuality. Specifically, MTCGM suggests to construct the multi-scale correlation tensor by stacking one self-correlation matrix and multiple surrounding-correlations of different scales, which well characterizes the network status of AIoT. Subsequently, a 3D-convolutional autoencoder (3DCA) is designed for capturing inter-feature correlations, and followed with a Gaussian mixture probability (GMP) network for the observations likelihood estimation. Moreover, low-dimensional space features, relative Euclidean distance and tensor cosine similarity (TCS) are adopted in MTCGM as the multi-factor to boost the likelihood estimation. Extensive experiments on public benchmark datasets verify the validity of MTCGM, and demonstrate its superiority over the state-of-the-art baselines even in presence of contaminated training samples and input noise. © 1975-2011 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

Toward High-Performance Delta-Based Iterative Processing with a Group-Based Approach

引用

Journal of Computer science & technology 2022年第4期37卷 797-813页

作者： Hui Yu Xin-Yu Jiang Jin Zhao Hao Qi Yu Zhang Xiao-Fei Liao Hai-Kun Liu Fu-Bing Mao Hai Jin National Engineering Research Center for Big Data Technology and System Huazhong University of Science and TechnologyWuhan 430074China Service Computing Technology and System Laboratory Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China

Many systems have been built to employ the delta-based iterative execution model to support iterative algorithms on distributed platforms by exploiting the sparse computational dependencies between data items of these iterative algorithms in a synchronous or asynchronous approach. However, for large-scale iterative algorithms, existing synchronous solutions suffer from slow convergence speed and load imbalance, because of the strict barrier between iterations;while existing asynchronous approaches induce excessive redundant communication and computation cost as a result of being barrier-free. In view of the performance trade-off between these two approaches, this paper designs an efficient execution manager, called Aiter-R, which can be integrated into existing delta-based iterative processing systems to efficiently support the execution of delta-based iterative algorithms, by using our proposed group-based iterative execution approach. It can efficiently and correctly explore the middle ground of the two extremes. A heuristic scheduling algorithm is further proposed to allow an iterative algorithm to adaptively choose its trade-off point so as to achieve the maximum efficiency. Experimental results show that Aiter-R strikes a good balance between the synchronous and asynchronous policies and outperforms state-of-the-art solutions. It reduces the execution time by up to 54.1% and 84.6% in comparison with existing asynchronous and the synchronous models, respectively.

关键词： iterative algorithm delta-based execution model efficiency

来源：评论

学校读者我要写书评

暂无评论

Discovering Cohesive Temporal Subgraphs with Temporal Density Aware Exploration

引用

Journal of Computer science & technology 2022年第5期37卷 1068-1085页

作者： Chun-Xue Zhu Long-Long Lin Ping-Peng Yuan Hai Jin National Engineering Research Center for Big Data Technology and System Huazhong University of Science and TechnologyWuhan 430074China Service Computing Technology and System Laboratory Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory Huazhong University of Science and TechnologyWuhan 430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China

Real-world networks,such as social networks,cryptocurrency networks,and e-commerce networks,always have occurrence time of interactions between *** networks are typically modeled as temporal *** cohesive subgraphs from temporal graphs is practical and essential in numerous data mining applications,since mining cohesive subgraphs gets insights into the time-varying nature of temporal ***,existing studies on mining cohesive subgraphs,such as Densest-Exact and k-truss,are mainly tailored for static graphs(whose edges have no temporal information).Therefore,those cohesive subgraph models cannot indicate both the temporal and the structural characteristics of *** this end,we explore the model of cohesive temporal subgraphs by incorporating both the evolving and the structural characteristics of temporal ***,the volume of time intervals in a temporal network is *** a result,the time complexity of mining temporal cohesive subgraphs is *** efficiently address the problem,we first mine the temporal density distribution of temporal *** by the distribution,we can safely prune many unqualified time intervals with the linear time ***,the remaining time intervals where cohesive temporal subgraphs fall in are examined using the greedy *** results of the experiments on nine real-world temporal graphs indicate that our model outperforms state-of-the-art solutions in efficiency and ***,our model only takes less than two minutes on a million-vertex DBLP and has the highest overall average ranking in EDB and TC metrics.

关键词： temporal network temporal feature distribution cohesive subgraph convex property

来源：评论

学校读者我要写书评

暂无评论

Real-time stealth transmission via dither-based bias control

Real-time stealth transmission via dither-based bias control

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Wang, Yuanxiang Shao, Weidong Zhong, Linsheng Dai, Xiaoxiao Yang, Qi Deng, Lei Liu, Deming Cheng, Mengfan Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan430074 China

We report a real-time 1 kbps stealthy transmission in the 10 Gbps QPSK public communication. The stealth data is embedded in dither signals of bias control. The scheme is compatible with existing optical transmission ... 详细信息

ISBN: (纸本)9781957171258

关键词： Light transmission

来源：评论

学校读者我要写书评

暂无评论

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage Cost KV-Separated LSM Store with SmartSSD-based GC Offloading 23

AegonKV: A High Bandwidth, Low Tail Latency, and Low Storage...

引用

23rd USENIX Conference on File and Storage Technologies, FAST 2025

作者： Duan, Zhuohui Feng, Hao Liu, Haikun Liao, Xiaofei Jin, Hai Li, Bangyu National Engineering Research Center for Big Data Technology and System Service Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology China

ISBN: (纸本)9781939133458

The key-value separation is renowned for its significant mitigation of the write amplification inherent in traditional LSM trees. However, KV separation potentially increases performance overhead in the management of Value region, especially for garbage collection (GC) operation that is used to reduce the redundant space occupation. In response, many efforts have been made to optimize the GC mechanism for KV separation. However, our analysis indicates that such solution based on trade-offs between CPU and I/O overheads cannot simultaneously satisfy the three requirements of KV separated systems in terms of throughput, tail latency, and space usage. This limitation hinders their real-world application. In this paper, we introduce AegonKV, a "three-birds-one-stone" solution that comprehensively enhances the throughput, tail latency, and space usage of KV separated systems. AegonKV first proposes a SmartSSD-based GC offloading mechanism to enable asynchronous GC operations without competing with LSM read/write for bandwidth or CPU. AegonKV leverages offload-friendly data structures and hardware/software execution logic to address the challenges of GC offloading. Experiments demonstrate that AegonKV achieves the largest throughput improvement of 1.28-3.3 times, a significant reduction of 37%-66% in tail latency, and 15%-85% in space overhead compared to existing KV separated systems. © 2025 FAST. All Rights Reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Efficient distributed algorithms for holistic aggregation functions on random regular graphs

引用

science China(Information sciences) 2022年第5期65卷 32-50页

作者： Lin JIA Qiang-Sheng HUA Haoqiang FAN Qiuping WANG Hai JIN National Engineering Research Center for Big Data Technology and System/Services Computing Technology and System Lab/Cluster and Grid Computing Lab School of Computer Science and TechnologyHuazhong University of Science and Technology Institute for Interdisciplinary Information Science Tsinghua University

In this paper, we propose efficient distributed algorithms for three holistic aggregation functions on random regular graphs that are good candidates for network topology in next-generation data *** three holistic aggregation functions include SELECTION（select the k-th largest or smallest element）,DISTINCT（query the count of distinct elements）, MODE（query the most frequent element）. We design three basic techniques — Pre-order Network Partition, Pairwise-independent Random Walk, and Random Permutation Delivery, and devise the algorithms based on the techniques. The round complexity of the distributed SELECTION is Θ（log N） which meets the lower bound where N is the number of nodes and each node holds a numeric element. The round complexity of the distributed DISTINCT and MODE algorithms are O（log3N/log log N） and O（log2N log log N） respectively. All of our results break the lower bounds obtained on general graphs and our distributed algorithms are all based on the CON GE S T model, which restricts each node to send only O（log N） bits on each edge in one round under synchronous communications.

关键词： distributed algorithms holistic aggregation function random regular graph $\mathcal{CONGEST}$ model communication complexity round complexity

来源：评论

学校读者我要写书评

暂无评论

ModelLock: Locking Your Model With a Spell 24

ModelLock: Locking Your Model With a Spell

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Gao, Yifeng Sun, Yuhua Ma, Xingjun Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Cs Fudan University Shanghai China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798400706868

This paper presents a novel model protection paradigm Model Locking that locks the performance of a finetuned model on private data to make it unusable or unextractable without the right key. Specifically, we proposed a diffusion-based framework dubbed ModelLock that explores text-guided image editing to transform the private finetuning data into unique styles or blend new objects into the background. A model finetuned on this edited dataset will be locked and can only be unlocked by the key prompt, i.e., the same text prompt used to edit the data. We conduct extensive experiments on both image classification and segmentation tasks and show that 1) ModelLock can effectively lock finetuned models without significantly reducing their unlocked performance, and more importantly, 2) the locked model cannot be easily unlocked without knowing both the key prompt and the diffusion model. Our work opens up a new direction for intellectual property protection of private models. © 2024 ACM.

关键词： Keys (for locks)

来源：评论

学校读者我要写书评

暂无评论

Machine Learning is All You Need: A Simple Token-Based Approach for Effective Code Clone Detection 24

Machine Learning is All You Need: A Simple Token-Based Appro...

引用

44th ACM/IEEE International Conference on Software engineering, ICSE 2024

作者： Feng, Siyue Suo, Wenqi Wu, Yueming Zou, Deqing Liu, Yang Jin, Hai Huazhong University of Science and Technology China Nanyang Technological University Singapore Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security China Jinyinhu Laboratory Wuhan430074 China School of Cyber Science and Engineering Hust Wuhan430074 China School of Computer Science and Technology Hust Wuhan430074 China

ISBN: (纸本)9798400702174

As software engineering advances and the code demand rises, the prevalence of code clones has increased. This phenomenon poses risks like vulnerability propagation, underscoring the growing importance of code clone detection techniques. While numerous code clone detection methods have been proposed, they often fall short in real-world code environments. They either struggle to identify code clones effectively or demand substantial time and computational resources to handle complex clones. This paper introduces a code clone detection method namely Toma using tokens and machine learning. Specifically, we extract token type sequences and employ six similarity calculation methods to generate feature vectors. These vectors are then input into a trained machine learning model for classification. To evaluate the effectiveness and scalability of Toma, we conduct experiments on the widely used bigCloneBench dataset. Results show that our tool outperforms token-based code clone detectors and most tree-based clone detectors, demonstrating high effectiveness and significant time savings. © 2024 ACM.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

TIPS:Tailored Information Extraction in Public security Using Domain-Enhanced Large Language Model

引用

Computers, Materials & Continua 2025年第5期83卷 2555-2572页

作者： Yue Liu Qinglang Guo Chunyao Yang Yong Liao School of Cyber Science and Technology University of Science and Technology of ChinaHefei230026China National Engineering Research Center for Public Safety Risk Perception and Control by Big Data China Academy of Electronics and Information TechnologyBeijing100041China

Processing police incident data in public security involves complex natural language processing(NLP)tasks,including information *** data contains extensive entity information—such as people,locations,and events—while also involving reasoning tasks like personnel classification,relationship judgment,and implicit ***,utilizing models for extracting information from police incident data poses a significant challenge—data scarcity,which limits the effectiveness of traditional rule-based and machine-learning *** address these,we propose *** collaboration with public security experts,we used de-identified police incident data to create templates that enable large language models(LLMs)to populate data slots and generate simulated data,enhancing data density and *** then designed schemas to efficiently manage complex extraction and reasoning tasks,constructing a high-quality dataset and fine-tuning multiple open-source *** showed that the fine-tuned ChatGLM-4-9B model achieved an F1 score of 87.14%,nearly 30%higher than the base model,significantly reducing error *** corrections further improved performance by 9.39%.This study demonstrates that combining largescale pre-trained models with limited high-quality domain-specific data can greatly enhance information extraction in low-resource environments,offering a new approach for intelligent public security applications.

关键词： Public security information extraction large language model prompt engineering

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：