检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Gao, Fei Hu, Ming Xie, Zhiyu Shi, Peichang Xie, Xiaofei Yi, Guodong Wang, Huaimin National Key Lab. of Parallel and Distributed Processing National University of Defense Technology Changsha China School of Computing and Information Systems Singapore Management University Singapore Xiangjiang Lab Changsha China

With advancements in AI infrastructure and Trusted Execution Environment (TEE) technology, Federated Learning as a Service (FLaaS) through JointCloud computing (JCC) is promising to break through the resource constraints caused by heterogeneous edge devices in the traditional Federated Learning (FL) paradigm. Specifically, with the protection from TEE, data owners can achieve efficient model training with high-performance AI services in the cloud. By providing additional FL services, cloud service providers can achieve collab.rative learning among data owners. However, FLaaS still faces three challenges, i.e., i) low training performance caused by heterogeneous data among data owners, ii) high communication overhead among different clouds (i.e., data centers), and iii) lack of efficient resource scheduling strategies to balance training time and cost. To address these challenges, this paper presents a novel asynchronous FL approach named NebulaFL for collab.rative model training among multiple clouds. To address data heterogeneity issues, NebulaFL adopts a version control-based asynchronous FL training scheme in each data center to balance training time among data owners. To reduce communication overhead, NebulaFL adopts a decentralized model rotation mechanism to achieve effective knowledge sharing among data centers. To balance training time and cost, NebulaFL integrates a reward-guided strategy for data owners selection and resource scheduling. The experimental results demonstrate that, compared to the state-of-the-art FL methods, NebulaFL can achieve up to 5.71% accuracy improvement. In addition, NebulaFL can reduce up to 50% communication overhead and 61.94% costs under a target accuracy. Copyright © 2024, The Authors. All rights reserved.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Intersecting-boundary-sensitive fingerprinting for tampering detection of DNN models 24

Intersecting-boundary-sensitive fingerprinting for tampering...

引用

Proceedings of the 41st International Conference on Machine Learning

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

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 lab.ls. 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 lab.ls. The IBSF code is availab.e at: https://***/CGCL-codes/IBSF.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong 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 Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensional Input Spaces

Detecting JVM JIT Compiler Bugs via Exploring Two-Dimensiona...

引用

International Conference on Software Engineering (ICSE)

作者： Haoxiang Jia Ming Wen Zifan Xie Xiaochen Guo Rongxin Wu Maolin Sun Kang Chen Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology China Hubei Key Laboratory of Distributed System Security Services Computing Technology and System Lab Cluster and Grid Computing Lab. Hubei Engineering Research Center on Big Data Security National Engineering Research Center for Big Data Technology and System School of Informatics Xiamen University China School of Computer Science and Technology Huazhong University of Science and Technology China

Java Virtual Machine (JVM) is the fundamental software system that supports the interpretation and execution of Java bytecode. To support the surging performance demands for the increasingly complex and large-scale Java programs, Just-In-Time (JIT) compiler was proposed to perform sophisticated runtime optimization. However, this inevitably induces various bugs, which are becoming more pervasive over the decades and can often cause significant consequences. To facilitate the design of effective and efficient testing techniques to detect JIT compiler bugs. This study first performs a preliminary study aiming to understand the characteristics of JIT compiler bugs and the corresponding triggering test cases. Inspired by the empirical findings, we propose JOpFuzzer, a new JVM testing approach with a specific focus on JIT compiler bugs. The main novelty of JOpFuzzer is embodied in three aspects. First, besides generating new seeds, JOpFuzzer also searches for diverse configurations along the new dimension of optimization options. Second, JOpFuzzer learns the correlations between various code features and different optimization options to guide the process of seed mutation and option exploration. Third, it leverages the profile data, which can reveal the program execution information, to guide the fuzzing process. Such nov-elties enable JOpFuzzer to effectively and efficiently explore the two-dimensional input spaces. Extensive evaluation shows that JOpFuzzer outperforms the state-of-the-art approaches in terms of the achieved code coverages. More importantly, it has detected 41 bugs in OpenJDK, and 25 of them have already been confirmed or fixed by the corresponding developers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Multi-Dimensional Assessment Model and Its Application in E-learning Courses of Computer Science 20

A Multi-Dimensional Assessment Model and Its Application in ...

引用

21st Annual Conference of the Special Interest Group in Information Technology Education, SIGITE 2020

作者： Luo, Jiwen Lu, Feng Wang, Tao Key Lab. of Parallel and Distributed Computing College of Computer National University of Defense Technology Changsha China 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 Technology Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9781450370455

Computer science is a practical discipline. It is always a great challenge to evaluate students' computer practice using computer-aided means for large scale students. We always need to address problems such as suspected plagiarism and deviation of the overall difficulty factor. In this paper, a multi-dimensional assessment model is designed for CS courses based on the detailed practice processing data in an E-learning system. The model comprehensively evaluates the students' learning process and results in three aspects of correctness, originality, and quality detection. Besides, the teacher can easily participate in the assessment according to their needs. The correctness is an essential requirement, and the originality is based on the clustering results of students' behaviors after clone detection to curb homework plagiarism. SonarQube is used to detect code quality and put forward higher requirements for codes. Manual participation intelligence has improved the flexibility and applicability of the model to a certain extent. We applied this model on the EduCoder online education platform and carried out a comprehensive analysis of 485 students in the Parallel Programming Principles and Practice Class of Huazhong University of Science and Technology. Experiment results confirm the distinction, rationality, and fairness of the model in assessing student performance. It not only gives students a credible, comprehensive score in large-scale online practical programming courses but also gives teachers and students corresponding suggestions based on the evaluation results. Furthermore, the model can be extended to other online education platforms. © 2020 ACM.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Espresso: Brewing Java for More Non-Volatility with Non-volatile Memory

arXiv

引用

arXiv 2017年

作者： Wu, Mingyu Zhao, Ziming Li, Haoyu Li, Heting Chen, Haibo Zang, Binyu Guan, Haibing Shanghai Key Lab. of Scalable Computing and Systems Institute of Parallel and Distributed Systems Shanghai Jiao Tong University

Fast, byte-addressable non-volatile memory (NVM) em-braces both near-DRAM latency and disk-like persistence, which has generated considerable interests to revolutionize system software stack and programming models. However, it is less understood how NVM can be combined with managed runtime like Java virtual machine (JVM) to ease persistence management. This paper proposes Espresso1, a holistic ex-tension to Java and its runtime, to enable Java programmers to exploit NVM for persistence management with high perfor-mance. Espresso first provides a general persistent heap de-sign called Persistent Java Heap (PJH) to manage persistent data as normal Java objects. The heap is then strengthened with a recoverable mechanism to provide crash consistency for heap metadata. It then provides a new abstraction called Persistent Java Object (PJO) to provide an easy-to-use but safe persistent programming model for programmers to per-sist application data. The evaluation confirms that Espresso significantly outperforms state-of-art NVM support for Java (i.e., JPA and PCJ) while being compatible to existing data structures in Java programs. Copyright © 2017, The Authors. All rights reserved.

关键词： Nonvolatile storage

来源：评论

学校读者我要写书评

暂无评论

Short: CICC: A fine-grained, semantic-aware, and transparent approach to preventing permission leaks for android permission managers 8

Short: CICC: A fine-grained, semantic-aware, and transparent...

引用

8th ACM Conference on Security and Privacy in Wireless and Mobile Networks, WiSec 2015

作者： Wang, Daibin Yao, Haixia Li, Yingjiu Jin, Hai Zou, Deqing Deng, Robert H. Services Computing Technology and System Lab. Cluster and Grid Computing Lab. School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China School of Information Systems Singapore Management University Singapore

ISBN: (纸本)9781450336239

Android's permission system offers an all-or-nothing installation choice for users. To make it more flexible, users may choose a popular app tool, called permission manager, to selectively grant or revoke an app's permissions at runtime. A fundamental requirement for such permission manager is that the granted or revoked permissions should be enforced faithfully. However, we discover that none of existing permission managers meet this requirement due to permission leaks. To address this problem, we propose CICC, a finegrained, semantic-aware, and transparent approach for any permission managers to defend against the permission leaks. Compared to existing solutions, CICC is fine-grained because it detects the permission leaks using call-chain information at the component instance level, instead of at the app level or component level. The fine-grained feature enables it to generate a minimal impact on the usability of running apps. CICC is semantic-aware in a sense that it manages call-chains in the whole lifecycle of each component instance. CICC is transparent to users and app developers, and it requires minor modification to permission managers. Our evaluation shows that CICC incurs relatively low performance overhead and power consumption. Copyright 2015 ACM.

关键词： Android Call-chain Permission leaks Permission manager

来源：评论

学校读者我要写书评

暂无评论

Self-Adaptive Extracting Academic Entities from World Wide Web

Self-Adaptive Extracting Academic Entities from World Wide W...

引用

International Conference on Collab.rative computing: Networking, Applications and Worksharing (Collab.rateCom)

作者： Pingpeng Yuan Yi Li Hai Jin Ling Liu Services Computing Technology and System Lab. Huazhong University of Science and Technology Wuhan China Distributed Data Intensive Systems Lab. Georgia Institute of Technology Atlanta Georgia

Huge amount of entities and theirs relationships are posted on the Web. Those entities and theirs relationship networks help many activities. In this paper, we focus on the task of extracting academic entity network from homepages. Homepages usually contain many entities, such as persons, conference/journal and organization and theirs relationship. However, homepages don't follow a unified layout format and often contains similar information, but differs greatly in layouts and styles, which makes it impossible to use a unified set of rules to handle them all. Thus we propose an integrated approach to automatically extract data from unstructured texts. The main idea of the approach is to adopt the most suitable approach to extract entities. Thus, the approach is self-adaptive. Firstly, the approach decomposes web pages into text units and then classifier is used to determine units' type. Once the units' types are known, the different technologies are chosen to deal with them. For example, edit distance and inverted index are used to identify names etc. And Conditional Random Field technology is considered the best solution to extract publication entries. The result shows that LineX has achieved high performance on extracting entities from web pages in academic community.

关键词： Web pages Data mining Knowledge based systems Electronic mail HTML Internet Organizations

来源：评论

学校读者我要写书评

暂无评论

A multi-resource load balancing algorithm for cloud cache systems 13

A multi-resource load balancing algorithm for cloud cache sy...

引用

28th Annual ACM Symposium on Applied computing, SAC 2013

作者： Jia, Yu Brondino, Ivan Peris, Ricardo Jiménez Martínez, Marta Patiño Ma, Dianfu Distributed Systems Lab. Universidad Politécnica de Madrid Spain Advanced Computing Technology Institute Beihang University China

ISBN: (纸本)9781450316569

With the advent of cloud computing model, distributed caches have become the cornerstone for building scalab.e applications. Popular systems like Facebook [1] or Twitter use Memcached [5], a highly scalab.e distributed object cache, to speed up applications by avoiding database accesses. distributed object caches assign objects to cache instances based on a hashing function, and objects are not moved from a cache instance to another unless more instances are added to the cache and objects are redistributed. This may lead to situations where some cache instances are overloaded when some of the objects they store are frequently accessed, while other cache instances are less frequently used. In this paper we propose a multi-resource load balancing algorithm for distributed cache systems. The algorithm aims at balancing both CPU and Memory resources among cache instances by redistributing stored data. Considering the possible conflict of balancing multiple resources at the same time, we give CPU and Memory resources weighted priorities based on the runtime load distributions. A scarcer resource is given a higher weight than a less scarce resource when load balancing. The system imbalance degree is evaluated based on monitoring information, and the utility load of a node, a unit for resource consumption. Besides, since continuous rebalance of the system may affect the QoS of applications utilizing the cache system, our data selection policy ensures that each data migration minimizes the system imbalance degree and hence, the total reconfiguration cost can be minimized. An extensive simulation is conducted to compare our policy with other policies. Our policy shows a significant improvement in time efficiency and decrease in reconfiguration cost. Copyright 2013 ACM.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Augmented reality and tangible user interfaces integration for enhancing the user experience

Augmented reality and tangible user interfaces integration f...

引用

11th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry, VRCAI 2012

作者： Rodrigues, Fábio Sato, Fernando Botega, Leonardo Oliveira, Allan Computing and Information Systems Research Lab. Centro Universitário Eurípides de Marília Brazil Wireless Networks and Distributed Interactive Simulations Laboratory Universidade Federal de São Carlos Brazil

ISBN: (纸本)9781450318259

The integration of post-wimp computer interfaces arises as an alternative to meet individual limitations of each one, considering both interaction components and feedbacks to users. Tangible interfaces can present restrictions referring to physical space on tabletop architectures, which limits the manipulation of objects and deprecates the interactive process. Hence, this paper proposes the integration of techniques of mobile Augmented Reality with tabletop tangible architecture for blending real and virtual components on its surface, aiming to make the interactive process richer, seamless and more complete. © 2012 ACM.

关键词： Augmented reality

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：