检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Bai, Xiaofan He, Chaoxiang Ma, Xiaojing Zhu, Bin Benjamin Jin, Hai School of Cyber Science and Engineering Huazhong University of Science and Technology China National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China Microsoft United States School of Computer Science and Technology Huazhong University of Science and Technology China Cluster and Grid Computing Lab China

Cloud-based AI services offer numerous benefits but also introduce vulnerabilities, allowing for tampering with deployed DNN models, ranging from injecting malicious behaviors to reducing computing resources. Fingerprint samples are generated to query models to detect such tampering. In this paper, we present Intersecting-Boundary-Sensitive Fingerprinting (IBSF), a novel method for black-box integrity verification of DNN models using only top-1 labels. Recognizing that tampering with a model alters its decision boundary, IBSF crafts fingerprint samples from normal samples by maximizing the partial Shannon entropy of a selected subset of categories to position the fingerprint samples near decision boundaries where the categories in the subset intersect. These fingerprint samples are almost indistinguishable from their source samples. We theoretically establish and confirm experimentally that these fingerprint samples' expected sensitivity to tampering increases with the cardinality of the subset. Extensive evaluation demonstrates that IBSF surpasses existing state-of-the-art fingerprinting methods, particularly with larger subset cardinality, establishing its state-of-the-art performance in black-box tampering detection using only top-1 labels. The IBSF code is available at: https://***/CGCL-codes/IBSF. Copyright 2024 by the author(s)

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

Towards High-throughput and Low-latency Billion-scale Vector Search via CPU/GPU Collaborative Filtering and Re-ranking 23

Towards High-throughput and Low-latency Billion-scale Vector...

引用

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

作者： Tian, Bing Liu, Haikun Tang, Yuhang Xiao, Shihai Duan, Zhuohui Liao, Xiaofei Jin, Hai Zhang, Xuecang Zhu, Junhua Zhang, Yu 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 Huawei Technologies Co. Ltd. China

ISBN: (纸本)9781939133458

Approximate nearest neighbor search (ANNS) has emerged as a crucial component of database and AI infrastructure. Ever-increasing vector datasets pose significant challenges in terms of performance, cost, and accuracy for ANNS services. None of modern ANNS systems can address these issues simultaneously. In this paper, we present FusionANNS, a high-throughput, low-latency, cost-efficient, and high-accuracy ANNS system for billion-scale datasets using SSDs and only one entry-level GPU. The key idea of FusionANNS lies in CPU/GPU collaborative filtering and re-ranking mechanisms, which significantly reduce I/O operations across CPUs, GPU, and SSDs to break through the I/O performance bottleneck. Specifically, we propose three novel designs: (1) multi-tiered indexing to avoid data swapping between CPUs and GPU, (2) heuristic re-ranking to eliminate unnecessary I/Os and computations while guaranteeing high accuracy, and (3) redundant-aware I/O deduplication to further improve I/O efficiency. We implement FusionANNS and compare it with the state-of-the-art SSD-based ANNS system-SPANN and GPU-accelerated in-memory ANNS system-RUMMY. Experimental results show that FusionANNS achieves 1) 9.4-13.1× higher query per second (QPS) and 5.7-8.8× higher cost efficiency compared with SPANN;2) and 2-4.9× higher QPS and 2.3-6.8× higher cost efficiency compared with RUMMY, while guaranteeing low latency and high accuracy. © 2025 FAST. All Rights Reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Autonomous Emergency Landing on 3D Terrains: Approaches for Monocular Vision-based UAVs 8

Autonomous Emergency Landing on 3D Terrains: Approaches for ...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Du, Weiming Lin, Junmou Du, Binqing Borhan, Uddin Md. Li, Jianqiang Chen, Jie College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China

ISBN: (纸本)9798350300178

With the increasing use of unmanned aerial vehicles (UAVs) in a variety of applications, their safety has become a critical concern. UAVs face numerous emergencies during missions, in these situations, the UAVs need to autonomously find a suitable landing site, plan flight routes, and avoid obstacles in unstructured environments. However, due to the limitations of computing power and sensors, it is challenging to achieve this goal. This research aims to explore the monocular emergency autonomous landing algorithm. Specifically, this work focuses on extracting depth and vision information. A topology information extractor is designed to convert image to graph and assess the connectivity of terrain. Additionally, a depth information extractor is designed to calculate the slope and roughness of the ground. A 3D topology optimizer is designed to optimize the graph by depth information and evaluate the landing suitability by a heuristic strategy. To make the action decision, a hybrid decision network (DGN) based on 3D topology information is proposed. Finally, this work build a simulated scenario based on real scene to verify the efficiency of DGN. The results of the experiment show that DGN outperforms its counterparts in terms of action prediction accuracy and landing success rate. © 2023 IEEE.

关键词： Landing

来源：评论

学校读者我要写书评

暂无评论

Defect Screening on Nuclear Power Plant Concrete Structures: A Two-staged Method Based on Contrastive Representation Learning 8

Defect Screening on Nuclear Power Plant Concrete Structures:...

引用

8th IEEE International Conference on Advanced Robotics and Mechatronics, ICARM 2023

作者： Huang, Wenlian Zhu, Guanming Huang, Qiang Chen, Zhuangzhuang Chen, Jie Li, Jianqiang College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China

ISBN: (纸本)9798350300178

Intelligent defect detection methods are important for the surface of the containment of nuclear power plants and face many challenges in the field of computer vision. Due to the irregular shapes and large variation of defects, as well as the similarity of the features between some defects and the background. Most existing deep learning-based defect detection networks suffer from insufficient feature extraction capabilities, making it difficult to detect defects from the background. Inspired by discrete representation learning methods, we propose a two-stage defect detection model called ConVQVAE, which uses a semi-supervised method for representation learning to achieve binary classification for defect detection. In addition, contrastive learning is performed in two stages to enhance the model's diversity representation ability and inter-class disentanglement representation ability. Finally, we experimentally verify that the proposed method can obtain good classification results. © 2023 IEEE.

关键词： Defects

来源：评论

学校读者我要写书评

暂无评论

IBATree: A Novel Method for Interpretable Cancer Cell Diagnosis Using Information Bottleneck Attribution

IBATree: A Novel Method for Interpretable Cancer Cell Diagno...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Raza, Muhammad Umair Chen, Jie Nawaz, Adil Saeed, Faisal Leung, Victor C.M. Li, Jianqiang Wang, Zhaoxia Shenzhen University College of Computer Science and Software Engineering China Shenzhen University National Engineering Laboratory for Big Data System Computing Technology China Shenzhen Children's Hospital Department of Gastroenterology China

ISBN: (纸本)9798350386226

Deep Neural Networks (DNNs) have demonstrated remarkable performance in classification and regression tasks on RGB-based pathological inputs. The network's prediction mechanism must be interpretable to establish trust in the clinical routine. One principal approach to interpretation is feature attribution. Feature attribution methods identify the importance of input features for the output prediction. Building on the Information Bottleneck Attribution (IBA) method, we recognize the RGB's input regions with high mutual information with the network's output for each prediction. IBA identifies input regions that have sufficient predictive information. In this paper, we introduce "IBATree", a novel approach that combines IBA with decision trees to enhance both the interpretability and accuracy of DNNs in cancer cell classification. Our method leverages the information bottleneck framework to inject noise into feature maps and then isolates the most informative features for model predictions while maintaining high classification performance. We evaluated our proposed approach on three datasets - CNMC, ISBI2016, and BreaKHis - demonstrating competitive accuracy and producing clear interpretations. This makes IBATree particularly suitable for clinical applications, where understanding the rationale behind predictions is crucial. Our results show that IBATree provides reliable predictions and valuable insights into feature importance, paving the way for its application in various biomedical domains. © 2024 IEEE.

关键词： Diseases

来源：评论

学校读者我要写书评

暂无评论

Unlearnable 3D Point Clouds: Class-wise Transformation Is All You Need 38

Unlearnable 3D Point Clouds: Class-wise Transformation Is Al...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Wang, Xianlong Li, Minghui Liu, Wei Zhang, Hangtao Hu, Shengshan Zhang, Yechao Zhou, Ziqi Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Computer Science and Technology Huazhong University of Science and Technology China

Traditional unlearnable strategies have been proposed to prevent unauthorized users from training on the 2D image data. With more 3D point cloud data containing sensitivity information, unauthorized usage of this new type data has also become a serious concern. To address this, we propose the first integral unlearnable framework for 3D point clouds including two processes: (i) we propose an unlearnable data protection scheme, involving a class-wise setting established by a category-adaptive allocation strategy and multi-transformations assigned to samples;(ii) we propose a data restoration scheme that utilizes class-wise inverse matrix transformation, thus enabling authorized-only training for unlearnable data. This restoration process is a practical issue overlooked in most existing unlearnable literature, i.e., even authorized users struggle to gain knowledge from 3D unlearnable data. Both theoretical and empirical results (including 6 datasets, 16 models, and 2 tasks) demonstrate the effectiveness of our proposed unlearnable framework. Our code is available at https://***/CGCL-codes/UnlearnablePC. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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

Towards Effective and Efficient Error Handling Code Fuzzing Based on Software Fault Injection 31

Towards Effective and Efficient Error Handling Code Fuzzing ...

引用

31st IEEE International Conference on Software Analysis, Evolution and Reengineering, SANER 2024

作者： Chen, Kang Wen, Ming Jia, Haoxiang Wu, Rongxin Jin, Hai Wuhan430074 China Jin YinHu Laboratory Wuhan430074 China School of Informatics Xiamen University Xiamen361005 China School of Computer Science and Technology HUST Wuhan430074 China National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab China Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security China Cluster and Grid Computing Lab China

ISBN: (纸本)9798350330663

Software systems often encounter various errors or exceptions in practice, and thus proper error handling code is essential to ensure the reliability of software systems. Unfortunately, error handling code is often bug-prone, while sufficiently testing them is challenging as such code often cannot be triggered under normal conditions. Motivated by this, recent studies have proposed to leverage software fault injection (SFI) based fuzzing to discover potential bugs in complicated error handling code. Despite the promising results achieved, their effectiveness and efficiency are still compromised in practice due to the huge search space of error sites, inadequate fuzzing guidance, and the overhead induced by context-sensitive SFI. To achieve effective and efficient testing of error handling code, this study presents AFL-FI, which first utilizes a similarity-based method to identify suspicious error sites, and then incorporates the idea of error site coverage to guide the fuzzing process. Finally, the design of lightweight context-sensitive SFI enables AFL-FI to execute test cases efficiently. We evaluate AFL-FI on eight large-scale open-source projects, and the results show that it can outperform existing state-of-the-art fuzzing tools significantly in terms of branch code coverage. More importantly, AFL-FI has discovered 13 previously unknown bugs, and all of them have been confirmed while 12 of them have been fixed. Besides, our evaluation also demonstrates that all the key designs of AFL-F I are effective that contribute significantly to its overall performance. © 2024 IEEE.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

A Survey of LLM datasets:From Autoregressive Model to AI Chatbot

引用

Journal of Computer Science & technology 2024年第3期39卷 542-566页

作者：杜非马新建杨婧如柳熠罗超然王学斌姜海鸥景翔 National Key Laboratory of Data Space Technology and System Beijing 100195China Advanced Institute of Big Data Beijing 100195China Fu Foundation School of Engineering and Applied Science Columbia UniversityNY 10027U.S.A. School of Software and Microelectronics Peking UniversityBeijing 100091China CCF IEEE

Since OpenAI opened access to ChatGPT,large language models(LLMs)become an increasingly popular topic attracting researchers’attention from abundant ***,public researchers meet some problems when developing LLMs given that most of the LLMs are produced by industries and the training details are typically *** datasets are an important setup of LLMs,this paper does a holistic survey on the training datasets used in both the pre-train and fine-tune *** paper first summarizes 16 pre-train datasets and 16 fine-tune datasets used in the state-of-the-art ***,based on the properties of the pre-train and fine-tune processes,it comments on pre-train datasets from quality,quantity,and relation with models,and comments on fine-tune datasets from quality,quantity,and *** study then critically figures out the problems and research trends that exist in current LLM *** study helps public researchers train and investigate LLMs by visual cases and provides useful comments to the research community regarding data *** the best of our knowledge,this paper is the first to summarize and discuss datasets used in both autoregressive and chat *** survey offers insights and suggestions to researchers and LLM developers as they build their models,and contributes to the LLM study by pointing out the existing problems of LLM studies from the perspective of data.

关键词： large language model(LLM) autoregressive model AI chatbot natural language processing(NLP)corpora OpenAI

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

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：