检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Jia, Zian Xiong, Yun Nan, Yuhong Zhang, Yao Zhao, Jinjing Wen, Mi Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Software Engineering Sun Yat-sen University China National Key Laboratory of Science and Technology on Information System Security China Shanghai University of Electric Power China

Advance Persistent Threats (APTs), adopted by most delicate attackers, are becoming increasing common and pose great threat to various enterprises and institutions. Data provenance analysis on provenance graphs has emerged as a common approach in APT detection. However, previous works have exhibited several shortcomings: (1) requiring attack-containing data and a priori knowledge of APTs, (2) failing in extracting the rich contextual information buried within provenance graphs and (3) becoming impracticable due to their prohibitive computation overhead and memory consumption. In this paper, we introduce MAGIC, a novel and flexible self-supervised APT detection approach capable of performing multi-granularity detection under different level of supervision. MAGIC leverages masked graph representation learning to model benign system entities and behaviors, performing efficient deep feature extraction and structure abstraction on provenance graphs. By ferreting out anomalous system behaviors via outlier detection methods, MAGIC is able to perform both system entity level and batched log level APT detection. MAGIC is specially designed to handle concept drift with a model adaption mechanism and successfully applies to universal conditions and detection scenarios. We evaluate MAGIC on three widely-used datasets, including both real-world and simulated attacks. Evaluation results indicate that MAGIC achieves promising detection results in all scenarios and shows enormous advantage over state-of-the-art APT detection approaches in performance overhead. Copyright © 2023, The Authors. All rights reserved.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Robust peer-to-peer learning via secure multi-party computation

引用

Journal of information and Intelligence 2023年第4期1卷 341-351页

作者： Yongkang Luo Wenjian Luo Ruizhuo Zhang Hongwei Zhang Yuhui Shi Guangdong Provincial Key Laboratory of Novel Security Intelligence Technologies School of Computer Science and TechnologyHarbin Institute of TechnologyShenzhen 518055China Peng Cheng Laboratory Shenzhen 518055China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Department of Computer Science and EngineeringSouthern University of Science and TechnologyShenzhen 518055China

To solve the data island problem,federated learning(FL)provides a solution paradigm where each client sends the model parameters but not the data to a server for model ***-to-peer(P2P)federated learning further improves the robustness of the system,in which there is no server and each client communicates directly with the *** secure aggregation,secure multi-party computing(SMPC)protocols have been utilized in peer-to-peer ***,the ideal SMPC protocols could fail when some clients drop *** this paper,we propose a robust peer-to-peer learning(RP2PL)algorithm via SMPC to resist clients dropping *** improve the segmentbased SMPC protocol by adding a check and designing the generation method of random seg*** RP2PL,each client aggregates their models by the improved robust secure multi-part computation protocol when finishes the local *** results demonstrate that the RP2PL paradigm can mitigate clients dropping out with no significant degradation in performance.

关键词： Federated learning Swarm learning Secure multi-party computation Peer-to-peer learning

来源：评论

学校读者我要写书评

暂无评论

Prior Knowledge-Driven Hybrid Prompter Learning for RGB-Event Tracking

引用

IEEE Transactions on Circuits and systems for Video technology 2025年

作者： Wang, Mianzhao Shi, Fan Cheng, Xu Chen, Shengyong Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System School of Computer Science and Engineering Tianjin300384 China Technical University of Denmark Department of Technology Management and Economics Kongens Lyngby Denmark

Event data can asynchronously capture variations in light intensity, thereby implicitly providing valuable complementary cues for RGB-Event tracking. Existing methods typically employ a direct interaction mechanism to fuse RGB and event data. However, due to differences in imaging mechanisms, the representational disparity between these two data types is not fixed, which can lead to tracking failures in certain challenging scenarios. To address this issue, we propose a novel prior knowledge-driven hybrid prompter learning framework for RGB-Event tracking. Specifically, we develop a frame-event hybrid prompter that leverages prior tracking knowledge from the foundation model as intermediate modal support to mitigate the heterogeneity between RGB and event data. By leveraging its rich prior tracking knowledge, the intermediate modal reduces the gap between the dense RGB and sparse event data interactions, effectively guiding complementary learning between modalities. Meanwhile, to mitigate the internal learning disparities between the lightweight hybrid prompter and the deep transformer model, we introduce a pseudo-prompt learning strategy that lies between full fine-tuning and partial fine-tuning. This strategy adopts a divide-and-conquer approach to assign different learning rates to modules with distinct functions, effectively reducing the dominant influence of RGB information in complex scenarios. Extensive experiments conducted on two public RGB-Event tracking datasets show that the proposed HPL outperforms state-of-the-art tracking methods, achieving exceptional performance. © 1991-2012 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

A Study on Semi-Supervised Semantic Segmentation of Ship Flame Images

A Study on Semi-Supervised Semantic Segmentation of Ship Fla...

引用

International Conference on Parallel and Distributed systems (ICPADS)

作者： Junwei Wan Yaojie Chen XueCong Zheng Department of Computer Science and Technology Wuhan University of Science and Technology Wuhan China Hubei Province Key Laboratory of Intelligent Information Processing and Real-Time Industrial System Wuhan China

In addressing the challenges of limited semantic labeling data and imprecise segmentation regions prevalent in the semantic segmentation of ship flame images, this study introduces a semi-supervised semantic segmentation method tailored for ship flame images. This approach is grounded in the principles of pairwise similarity with strong-weak perturbations. Adopting a pseudo-label self-learning strategy, the method employs weak-strong perturbation pairwise similarity, ensuring the propagation of high-confidence predictions during label generation, and thereby enhancing performance. Additionally, to tackle the inherent difficulties presented by smoke enveloping and obscuring flame regions in ship images, we have conceived a Vertical Continuity Feature Enhancement module. This module empowers the model to discern more explicit inter-class boundaries. Empirical evaluations on our proprietary dataset substantiate the superiority of our method, registering an improvement of 4.12 percentage points in mIoU over other semi-supervised approaches. Such results attest to the efficacy of the proposed pairwise similarity approach and the Vertical Continuity Feature Enhancement module in flame semantic segmentation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Topic-sensitive neural headline generation

引用

science China(information sciences) 2020年第8期63卷 180-195页

作者： Ayana Ziyun WANG Lei XU Zhiyuan LIU Maosong SUN State Key Laboratory of Intelligent Technology and Systems Tsinghua National Laboratory for Information Science and TechnologyDepartment of Computer Science and TechnologyTsinghua University Department of Computer Information Management Inner Mongolia University of Finance and Economics

Neural models are being widely applied for text summarization, including headline generation,and are typically trained using a set of document-headline pairs. In a large document set, documents can usually be grouped into various topics, and documents within a certain topic may exhibit specific summarization patterns. Most existing neural models, however, have not taken the topic information of documents into consideration. This paper categorizes documents into multiple topics, since documents within the same topic have similar content and share similar summarization patterns. By taking advantage of document topic information, this study proposes a topic-sensitive neural headline generation model(TopicN HG). It is evaluated on a real-world dataset, large scale Chinese short text summarization dataset. Experimental results show that it outperforms several baseline systems on each topic and achieves comparable performance with the state-of-the-art system. This indicates that TopicN HG can generate more accurate headlines guided by document topics.

关键词： neural networks sequence to sequence learning topic LDA headline generation

来源：评论

学校读者我要写书评

暂无评论

OmniMark: Efficient and Scalable Latent Diffusion Model Fingerprinting 39

OmniMark: Efficient and Scalable Latent Diffusion Model Fing...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Fei, Jianwei Dai, Yunshu Xia, Zhihua Huang, Fangjun Zhou, Jiantao State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science University of Macau China School of Cyber Science and Technology Sun Yat-Sen University China College of Cyberspace Security Jinan University China

ISBN: (纸本)157735897X

We introduce OmniMark, a novel and efficient fingerprinting method for Latent Diffusion Models (LDM). OmniMark can encode user-specific fingerprints across diverse dimensions of the weights of the LDM, including kernels, filters, channels, and spatial domains. The LDM is fine-tuned to encode the invisible fingerprint into generated images, which can be decoded by a decoder. By altering fingerprints and re-encoding the weights, OmniMark supports efficient and scalable adhoc generation ( Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Ethereum smart contract security research:survey and future research opportunities

引用

Frontiers of computer science 2021年第2期15卷 143-160页

作者： Zeli WANG Hai JIN Weiqi DAI Kim-Kwang Raymond CHOO Deqing ZOU National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabHubei Engineering Research Center on Big Data SecurityWuhan430074China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan430074China School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan430074China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen518057China Department of Information Systems and Cyber Security University of Texas at San AntonioSan AntonioTX78249-0631USA

Blockchain has recently emerged as a research trend,with potential applications in a broad range of industries and *** particular successful Blockchain technology is smart contract,which is widely used in commercial settings(e.g.,high value financial transactions).This,however,has security implications due to the potential to financially benefit from a security incident(e.g.,identification and exploitation of a vulnerability in the smart contract or its implementation).Among,Ethereum is the most active and ***,in this paper,we systematically review existing research efforts on Ethereum smart contract security,published between 2015 and ***,we focus on how smart contracts can be maliciously exploited and targeted,such as security issues of contract program model,vulnerabilities in the program and safety consideration introduced by program execution *** also identify potential research opportunities and future research agenda.

关键词： smart contract security blockchain vulnerability unreliable data

来源：评论

学校读者我要写书评

暂无评论

Efficient Routing Protection Algorithm Based on Optimized Network Topology

引用

computers, Materials & Continua 2022年第9期72卷 4525-4540页

作者： Haijun Geng Zikun Jin Jiangyuan Yao Han Zhang Zhiguo Hu Bo Yang Yingije Guo Wei Wang Qidong Zhang Guoao Duan School of Computer and Information Technology Shanxi UniversityShanxi030006China School of Automation and Software Engineering Shanxi UniversityShanxi030006China School of Computer Science and Technology Hainan UniversityHaikou570228China Department of Computer Science&Technology Tsinghua UniversityBeijing100084China Department of Urban&Regional Planning San JoséState University San JoséCA95192USA Key Laboratory of Embedded System and Service Computing(Tongji University) Ministry of EducationShanghai201804China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of ChinaChengdu610054China Beijinng University of Technology Beijing-Dublin International CollegeBeijing University of TechnologyBeijing100124China

Network failures are unavoidable and occur *** the network fails,intra-domain routing protocols deploying on the Internet need to undergo a long convergence *** this period,a large number of messages are discarded,which results in a decline in the user experience and severely affects the quality of service of Internet Service Providers(ISP).Therefore,improving the availability of intra-domain routing is a trending research question to be *** usually employs routing protection algorithms to improve intra-domain routing ***,existing routing protection schemes compute as many backup paths as possible to reduce message loss due to network failures,which increases the cost of the network and impedes the methods deployed in *** address the issues,this study proposes an efficient routing protection algorithm based on optimized network topology(ERPBONT).ERPBONT adopts the optimized network topology to calculate a backup path with the minimum path coincidence degree with the shortest path for all source ***,the backup path with the minimum path coincidence with the shortest path is described as an integer programming *** the simulated annealing algorithm ERPBONT is used to find the optimal ***,the algorithm is tested on the simulated topology and the real *** experimental results show that ERPBONT effectively reduces the path coincidence between the shortest path and the backup path,and significantly improves the routing availability.

关键词： Routing protection algorithm network availability network failure shortest path backup path

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

arXiv

引用

arXiv 2024年

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 Services Computing Technology and System Lab Cluster and Grid Computing Lab Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security 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 Copyright © 2024, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neo: Towards Efficient Fully Homomorphic Encryption Acceleration using Tensor Core 25

Neo: Towards Efficient Fully Homomorphic Encryption Accelera...

引用

Proceedings of the 52nd Annual International Symposium on computer Architecture

作者： Dian Jiao Xianglong Deng Zhiwei Wang Shengyu Fan Yi Chen Dan Meng Rui Hou Mingzhe Zhang State Key Laboratory of Cyberspace Security Defense Institute of Information Engineering CAS Beijing China and School of Cyber Security University of Chinese Academy of Sciences Beijing China State Key Laboratory of Cyberspace Security Defense Institute of Information Engineering CAS Beijing China Huazhong University of Science and Technology Wuhan China Computing System Lab Ant Group Beijing China

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：