检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Web services, ICWS 2023

作者： Wang, Cheng Chai, Songyao Zhu, Hangyu Department of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education China Shanghai Artificial Intelligence Laboratory Shanghai China

ISBN: (纸本)9798350304855

The rapid growth of electronic commerce brings convenience to modern life but comes with security risks by various cybercrimes in online payment services. Most existing security methods for fraud detection depend on the static learning paradigm, which trains a model over a static training dataset and deploys the trained model for inference with the frozen model parameters under the i.i.d. assumption. Unfortunately, this paradigm becomes incommensurate with the increasingly complicated and varying fraud patterns due to the untimely and delayed responses in the offline environment. Without sensing the evolution of fraud timely, it is challenging to train and deploy targeted countermeasures. The emerging means of fraud are not only reflected in the openness of their category, but also in the drift of their superimposed risk features. The interweaving of open-category and concept drift accelerates the process of existing methods becoming powerless. In this paper, we propose EvoFD, an online evolving fraud detection framework to enable continual learning to cope with undercurrent surges of evolving fraud. The core idea of EvoFD is to weaken the bias caused by the anchoring effect on the learned information. It learns in an online streaming fashion by using instructive representations as anchors. Specially, we maintain the progressively updatable class anchors and optimize the representation network to embed features and class anchors into a unified normalized space, where the training and predicting can be conducted simultaneously or independently. In the framework, we preserve the balanced replay memory for each class to accumulate knowledge and avoid forgetting. The advantages of our method are validated by extensive experiments over the real-world dataset from a prestigious bank. © 2023 IEEE.

关键词： Crime

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Heterogeneous Credit Card Fraud Detection Model Based on Deep Reinforcement Training Subset Selection

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4026-4041页

作者： Zhu, Kun Zhang, Nana Ding, Weiping Jiang, Changjun the Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai201804 China Collaborative Innovation Center for Financial Network Security Tongji University Shanghai201804 China the School of Computer Science and Technology Donghua University Shanghai201620 China the School of Information Science and Technology Nantong University Nantong226019 China

Heterogeneous fraud detection is an important means of credit card security assurance, which can utilize historical transaction records in a source and target domain to build an effective fraud detection model. Nevertheless, large feature distribution differences between source and target transaction instances and the complex intrinsic structure hidden behind transaction data make it difficult for existing credit card fraud detection (CCFD) models to capture and transfer the most informative feature representations and seriously hinder detection performance. In this work, we propose a novel adaptive heterogeneous CCFD model named adaptive heterogeneous credit card fraud detection model based on deep reinforcement training subset selection (RTAHC) based on deep reinforcement training subset selection, which mainly contains two components: selection distribution generator (SDG) and transaction fraud detector (TFD, including feature extractor with an attention mechanism and classifier). The SDG can generate the selection probability distribution vector via the reinforcement reward mechanism, and then transaction instances in the source domain relevant to the target domain are selected. The feature extractor with an attention mechanism can learn the abstract deep semantic feature representations of selected source transaction instances and the target domain. The joint training of SDG and TFD can provide more real-time and accurate transaction feature representations to reduce the distribution discrepancy between the two domains. We verify the detection performance of RTAHC across a large real-world credit card transaction dataset and four public datasets. Experimental results demonstrate that the RTAHC model can exhibit competitive CCFD performance. Impact Statement—With the rise of artificial intelligence (AI)generated models, credit card fraud has become increasingly rampant, which also causes tens of billions of U.S. dollars in credit card losses worldwide every year

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

ST-ReP: Learning Predictive Representations Efficiently for Spatial-Temporal Forecasting

arXiv

引用

arXiv 2024年

作者： Zheng, Qi Yao, Zihao Zhang, Yaying The Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University Shanghai200092 China

Spatial-temporal forecasting is crucial and widely applicable in various domains such as traffic, energy, and climate. Benefiting from the abundance of unlabeled spatial-temporal data, self-supervised methods are increasingly adapted to learn spatial-temporal representations. However, it encounters three key challenges: 1) the difficulty in selecting reliable negative pairs due to the homogeneity of variables, hindering contrastive learning methods;2) overlooking spatial correlations across variables over time;3) limitations of efficiency and scalability in existing self-supervised learning methods. To tackle these, we propose a lightweight representation-learning model ST-ReP, integrating current value reconstruction and future value prediction into the pre-training framework for spatial-temporal forecasting. And we design a new spatial-temporal encoder to model fine-grained relationships. Moreover, multi-time scale analysis is incorporated into the self-supervised loss to enhance predictive capability. Experimental results across diverse domains demonstrate that the proposed model surpasses pre-training-based baselines, showcasing its ability to learn compact and semantically enriched representations while exhibiting superior scalability. Copyright © 2024, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Better Cardinality Estimator with Fewer Bits, Constant Update Time, and Mergeability 42

A Better Cardinality Estimator with Fewer Bits, Constant Upd...

引用

42nd IEEE International Conference on Computer Communications, INFOCOM 2023

作者： Du, Yang Huang, He Sun, Yu-E Li, Kejian Zhang, Boyu Gao, Guoju Soochow University School of Computer Science and Technology Suzhou China Soochow University School of Rail Transportation Suzhou China Ministry of Education Key Laboratory of Embedded System and Service Computing Shanghai China

ISBN: (纸本)9798350334142

Cardinality estimation is a fundamental problem with diverse practical applications. HyperLogLog (HLL) has become a standard in practice because it offers good memory efficiency, constant update time, and mergeability. Some recent work achieved better memory efficiency, but typically at the cost of impractical update time or losing mergeability, making them incompatible with applications like network-wide traffic measurement. This work presents SpikeSketch, a better cardinality estimator that reduces memory usage of HLL by 37% without sacrificing other crucial metrics. We adopt a bucket-based data structure to promise constant update time, design a smoothed log4 ranking and a spike coding scheme to compress cardinality observables into buckets, and propose a lightweight mergeable lossy compression to balance memory usage, information loss, and mergeability. Then we derive an unbiased estimator for recovering cardinality from the lossy-compressed sketch. Theoretical and empirical results show that SpikeSketch can work as a drop-in replacement for HLL because it achieves a near-optimal MVP (memory-variance-product) of 4.08 (37% smaller than HLL) with constant update time and mergeability. Its memory efficiency even defeats ACPC and HLLL, the state-of-the-art lossless-compressed sketches using linear-time compression to reduce memory usage. © 2023 IEEE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Meta-Heuristic Based Multipath Joint Routing and Scheduling of Time-Triggered Traffic for Time-Sensitive Networking in IIoT 2

Meta-Heuristic Based Multipath Joint Routing and Scheduling ...

引用

2nd International Conference on Green Communication, Network, and Internet of Things, CNIoT 2022

作者： Chen, Chen Li, Zhong The College of Information Science and Technology Donghua University Shanghai201620 China The Key Laboratory of the Ministry of Education for Embedded System and Service Computing Department of Computer Science Tongji University Shanghai201804 China

ISBN: (纸本)9781510662940

Time-Sensitive networking (TSN) meets the needs of industrial internet of things (IIoT). It solves the challenges of deterministic transmission and reliable communication of time sensitive data streams. Traffic scheduling is the core mechanism of time-sensitive networks. Many excellent researches have explored and optimized the method of scheduling time-triggered streams in TSN. However, the existing time-triggered streams scheduling in TSN mostly separates routing and scheduling, which limits the scalability of scheduling. Many researches are based on fixed routing to schedule streams. Due to the interaction between scheduling and routing, the quality of fixed route solution is inferior to that of joint routing and scheduling. In this paper, we propose a meta-heuristic based multipath joint routing and scheduling method for time-triggered traffic in TSN, named MMRS. We set path selection as a variable and consider multipath routing for fault tolerance. At the same time, we establish the integer linear programming formulation and use meta-heuristic to obtain high-quality solutions. The evaluations show that compared with other excellent routing and scheduling methods, the runtime of 60 streams of MMRS method is reduced by 65.6%, and the schedulability is improved by 21% on average. The experiments verify that our proposed scheduling method can obtain high-quality solutions in an acceptable solution time. © 2023 SPIE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

BMSAD: Behavior Feature and Multi-Scenario -Based Sybil Attack Detection Method in Vehicular Networks 3

BMSAD: Behavior Feature and Multi-Scenario -Based Sybil Atta...

引用

3rd International Seminar on Artificial Intelligence, Networking, and Information Technology, AINIT 2022

作者： Luo, Jie Li, Zhong College of Information Science and Technology Donghua University Shanghai201620 China Key Laboratory of the Ministry of Education for Embedded System and Service Computing Department of Computer Science Tongji University Shanghai201804 China

ISBN: (数字)9781510662971

ISBN: (纸本)9781510662964

Vehicular networks improve traffic safety and efficiency by wireless communications among vehicles and infrastructures. However, security has always been a challenge to vehicular networks, which may cause severe harm to the intelligent transportation systems. Sybil attack is considered as a serious security threat to vehicular networks since the attacker can disseminate false messages with multiple forged identities. In this paper, we designed a behavior feature and multi-scenario-based Sybil attack detection method, named BMSAD in vehicular networks. In BMSAD, we propose solutions for two scenarios: normal traffic and traffic congestion. A node is allowed to verify the authenticity of another node by estimating their geographic distance based on received signal strength, and compare them to its claimed localizations. Then we design long- and short-term pattern to analyze the similarity of vehicles' behavior features and trajectory for Sybil nodes detection, which act as the second line of defense in normal traffic scenario. At last, the Sybil nodes of the traffic congestion scenario are detected by logical inference based on kinematics theory. And experiment results demonstrate that the proposed scheme achieves high detection rate and low false positive rate. © 2023 SPIE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

Information Security Evaluation by Information Flow Analysis Based on Stochastic Petri Nets

Information Security Evaluation by Information Flow Analysis...

引用

2024 IEEE International Conference on systems, Man, and Cybernetics, SMC 2024

作者： Tu, Hanqian Xiang, Dongming Lin, Wang Liu, Guanjun Zhejiang Sci-Tech University Department of Computer Science and Technology Hangzhou310018 China Shanghai Electronic Transactions and Information Service Collaborative Innovation Center Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Department of Computer Science Shanghai201804 China

ISBN: (纸本)9781665410205

The Petri-net-based information flow analysis offers an effective approach for detecting information leakage by the concept of non-interference. Although the related studies propose efficient solutions, they lack quantitative evaluation on information leakage. In this paper, we propose a novel method for quantitative evaluation of information security based on stochastic labeled Petri nets (SLPNs) and information flow analysis. Specifically, we introduce four different levels of security metrics, and provide a methodology for evaluating the information security. Furthermore, a case study is presented to show the feasibility of our method. © 2024 IEEE.

关键词： Information leakage

来源：评论

学校读者我要写书评

暂无评论

Discretized Gaussian Mixture Hyperprior for Learned Image Compression with Mask Module

Discretized Gaussian Mixture Hyperprior for Learned Image Co...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Wang, Shengkai Wang, Hanli Tongji University Department of Computer Science and Technology Shanghai China Tongji University Key Laboratory of Embedded System and Service Computing Ministry of Education Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Learned image compression approaches have shown great potential with promising results. However, according to the commonly used measurement methods, there still lies a performance gap between learned compression methods and the latest compression standard versatile video coding (VVC), because of the remaining redundancy existing in contemporary algorithms. To obtain a more accurate entropy model for rate estimation, discretized Gaussian mixture hyperprior is proposed in this work to parameterize the distribution of latent codes. In addition, a proposed mask module is exploited to enhance the feature extraction ability of the encoder and adaptively allocate bit rates. In this case, the proposed learned image compression model achieves the state-of-the-art performance among the existing learned compression methods and most compression standards on both Kodak24 and CLIC Mobile Validation datasets. The proposed model also outperforms VVC under several bitrate scenarios. © 2022 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

UAV-Mounted Intelligent Reflecting Surface in Maritime Wireless Powered Communication Network

引用

China Communications 2025年第3期22卷 254-269页

作者： Liu Yuan Han Fengxia Zhao Shengjie School of Information Science and Electrical Engineering Shandong Jiaotong UniversityJinan 250357China College of Electronic and Information Engineering Tongji UniversityShanghai 201804China School of Software Engineering Tongji UniversityShanghai 201804China Engineering Research Center of Key Software Technologies for Smart City Perception and Planning Ministry of EducationShanghai 200003China Key Laboratory of Embedded System and Service Computing Tongji University Shanghai 201804China

Intelligent reflecting surface(IRS)assisted with the wireless powered communication network(WPCN)can enhance the desired signal energy and carry out the power-sustaining problem in ocean monitoring *** this paper,we investigate a reliable communication structure where multiple buoys transmit data to a base station(BS)with the help of the unmanned aerial vehicle(UAV)-mounted IRS and harvest energy from the base station *** organically combine WPCN with maritime data collection scenario,a scheduling protocol that employs the time division multiple access(TDMA)is proposed to serve multiple buoys for uplink data ***,we compare the full-duplex(FD)and half-duplex(HD)mechanisms in the maritime data collection system to illustrate different performances under these two *** maximize the fair energy efficiency under the energy harvesting constraints,a joint optimization problem on user association,BS transmit power,UAV’s trajectory and IRS’s phase shift is *** solve the non-convex problem,the original problem is decoupled into several subproblems,and successive convex optimization and block coordinate descent(BCD)methods are employed obtain the near-optimal solutions *** results demonstrate that the UAV-mounted IRS can significantly improve energy efficiency in our considered system.

关键词： full-duplex IRS joint optimization TDMA UAV WPCN

来源：评论

学校读者我要写书评

暂无评论

Attack by Yourself: Effective and Unnoticeable Multi-Category Graph Backdoor Attacks with Subgraph Triggers Pool

arXiv

引用

arXiv 2024年

作者： Li, Jiangtong Liu, Dongyi Cheng, Dawei Jiang, Changjun School of Computer Science and Technology Tongji University Shanghai China Key Laboratory of Embedded System and Service Computing Ministry of Education China

Graph Neural Networks (GNNs) have achieved significant success in various real-world applications, including social networks, finance systems, and traffic management. Recent researches highlight their vulnerability to backdoor attacks in node classification, where GNNs trained on a poisoned graph misclassify a test node only when specific triggers are attached. These studies typically focus on single attack categories and use adaptive trigger generators to create node-specific triggers. However, adaptive trigger generators typically have a simple structure, limited parameters, and lack category-aware graph knowledge, which makes them struggle to handle backdoor attacks across multiple categories as the number of target categories increases. We address this gap by proposing a novel approach for Effective and Unnoticeable Multi-Category (EUMC) graph backdoor attacks, leveraging subgraph from the attacked graph as category-aware triggers to precisely control the target category. To ensure the effectiveness of our method, we construct a Multi-Category Subgraph Triggers Pool (MC-STP) using the subgraphs of the attacked graph as triggers. We then exploit the attachment probability shifts of each subgraph trigger as category-aware priors for target category determination. Moreover, we develop a "select then attach" strategy that connects suitable category-aware trigger to attacked nodes for unnoticeability. Extensive experiments across different real-world datasets confirm the efficacy of our method in conducting multi-category graph backdoor attacks on various GNN models and defense strategies. © 2024, CC BY-NC-SA.

关键词： Graph neural networks

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

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

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：