检索结果-内蒙古大学图书馆

Tile Classification Based Viewport Prediction with Multi-modal Fusion Transformer

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Zhihao Chen, Yiwei Zhang, Weizhan Yan, Caixia Zheng, Qinghua Wang, Qi Chen, Wangdu School of Computer Science and Technology Xi'an Jiaotong University Key Laboratory of Intelligent Networks and Network Security Ministry of Education Xi'an Jiaotong University Xi’an China School of Computer Science and Technology Xi'an Jiaotong University & National Engineering Lab for Big Data Analytics Xi'an Jiaotong University Xi’an China MIGU Video Shanghai China

Viewport prediction is a crucial aspect of tile-based 360◦ video streaming system. However, existing trajectory based methods lack of robustness, also oversimplify the process of information construction and fusion between different modality inputs, leading to the error accumulation problem. In this paper, we propose a tile classification based viewport prediction method with Multi-modal Fusion Transformer, namely MFTR. Specifically, MFTR utilizes transformer-based networks to extract the long-range dependencies within each modality, then mine intra- and inter-modality relations to capture the combined impact of user historical inputs and video contents on future viewport selection. In addition, MFTR categorizes future tiles into two categories: user interested or not, and selects future viewport as the region that contains most user interested tiles. Comparing with predicting head trajectories, choosing future viewport based on tile's binary classification results exhibits better robustness and interpretability. To evaluate our proposed MFTR, we conduct extensive experiments on two widely used PVS-HM and Xu-Gaze dataset. MFTR shows superior performance over state-of-the-art methods in terms of average prediction accuracy and overlap ratio, also presents competitive computation efficiency. © 2023, CC BY.

关键词： Forecasting

PPA: Preference Profiling Attack Against Federated Learning

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zhou, Chunyi Gao, Yansong Fu, Anmin Chen, Kai Dai, Zhiyang Zhang, Zhi Xue, Minhui Zhang, Yuqing School of Computer Science and Engineering Nanjing University of Science and Technology China State Key Laboratory of Information Security Institute of Information Engineering Chinese Academy of Science China Data61 CSIRO Sydney Australia National Computer Network Intrusion Protection Center University of Chinese Academy of Science China

Federated learning (FL) trains a global model across a number of decentralized users, each with a local dataset. Compared to traditional centralized learning, FL does not require direct access to local datasets and thus aims to mitigate data privacy concerns. However, data privacy leakage in FL still exists due to inference attacks, including membership inference, property inference, and data inversion. Copyright © 2022, The Authors. All rights reserved.

关键词： data privacy

Disentangled Noisy Correspondence Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Dang, Zhuohang Luo, Minnan Wang, Jihong Jia, Chengyou Han, Haochen Wan, Herun Dai, Guang Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi'An710049 China SGIT AI Lab State Grid Shaanxi Electric Power Company Limited State Grid Corporation of China Shaanxi China The School of Information Science and Technology University of Science and Technology China United Arab Emirates The Baidu Inc China

Cross-modal retrieval is crucial in understanding latent correspondences across modalities. However, existing methods implicitly assume well-matched training data, which is impractical as real-world data inevitably involves imperfect alignments, i.e., noisy correspondences. Although some works explore similarity-based strategies to address such noise, they suffer from sub-optimal similarity predictions influenced by modality-exclusive information (MEI), e.g., background noise in images and abstract definitions in texts. This issue arises as MEI is not shared across modalities, thus aligning it in training can markedly mislead similarity predictions. Moreover, although intuitive, directly applying previous cross-modal disentanglement methods suffers from limited noise tolerance and disentanglement efficacy. Inspired by the robustness of information bottlenecks against noise, we introduce DisNCL, a novel information-theoretic framework for feature Disentanglement in Noisy Correspondence Learning, to adaptively balance the extraction of MII and MEI with certifiable optimal cross-modal disentanglement efficacy. DisNCL then enhances similarity predictions in modality-invariant subspace, thereby greatly boosting similarity-based alleviation strategy for noisy correspondences. Furthermore, DisNCL introduces soft matching targets to model noisy many-to-many relationships inherent in multi-modal input for noise-robust and accurate cross-modal alignment. Extensive experiments confirm DisNCL's efficacy by 2% average recall improvement. Mutual information estimation and visualization results show that DisNCL learns meaningful MII/MEI subspaces, validating our theoretical analyses. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

Demand Response Scheme: Achieving Sustainability in Distributed data Processing

学校读者我要写书评

暂无评论

Demand Response Scheme: Achieving Sustainability in Distribu...

IEEE International Conference on data Science in Cyberspace (DSC)

作者： Xueying Zhai Yunfeng Peng Xiuping Guo Liang Zhang Wei Zhang School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China School of Economics and Management Beijing University of Posts and Telecommunications Beijing China Guizhou Key Laboratory of Electric Power Big Data Guizhou Institute of Technology Guizhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

The rapid development of Internet of Things (IoT) technology has driven the intelligent transformation of various industries, including manufacturing, agriculture, and healthcare, etc., significantly enhancing their management capabilities and decision-making efficiency. data analysis is crucial, serving as both the core technology of this transformation and a major driving force for advancing industry intelligence. However, the increasing volume of data has led to high energy consumption during data analysis, posing significant challenges to environmental and economic sustainability. Integrating renewable energy sources (RESs) is an effective way to reduce greenhouse gas emissions due to their low-carbon and renewable nature. Additionally, the spatiotemporal variability and complementarity of RES generation and grid electricity prices provide favorable conditions for distributed data processing. Therefore, a two-stage demand response scheme is proposed to reduce carbon emissions and electricity costs by prioritizing data processing in data centers (DCs) where RES is abundant or electricity prices are low, based on RES generation and electricity price signals. Simulation results show that the proposed scheme reduces 36.37% carbon emissions and 20.49% electricity costs compared to the benchmark algorithm, indicating its potential for both environmental and economic optimization.

关键词： Renewable energy sources Energy consumption Costs Electricity Simulation Carbon dioxide Spatiotemporal phenomena Internet of Things Sustainable development Optimization

TRUST: A Toolkit for TEE-Assisted Secure Outsourced Computation over Integers

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhao, Bowen Li, Jiuhui Xu, Peiming Li, Xiaoguo Pei, Qingqi Shen, Yulong Guangzhou Institute of Technology Xidian University Guangzhou510555 China State Key Laboratory of Public Big Data Guizhou University Guiyang550025 China Electric Power Research Institute CSG Guangdong Guangzhou510663 China Guangdong Provincial Key Laboratory of Power System Network Security Guangdong Guangzhou510663 China The College of Computer Science Chongqing University Chongqing400044 China The State Key Laboratory of Integrated Service Networks Xidian University Xi’an710126 China

Secure outsourced computation (SOC) provides secure computing services by taking advantage of the computation power of cloud computing and the technology of privacy computing (e.g., homomorphic encryption). Expanding computational operations on encrypted data (e.g., enabling complex calculations directly over ciphertexts) and broadening the applicability of SOC across diverse use cases remain critical yet challenging research topics in the field. Nevertheless, previous SOC solutions frequently lack the computational efficiency and adaptability required to fully meet evolving demands. To this end, in this paper, we propose a toolkit for TEE-assisted (Trusted Execution Environment) SOC over integers, named TRUST. In terms of system architecture, TRUST falls in a single TEE-equipped cloud server only through seamlessly integrating the computation of REE (Rich Execution Environment) and TEE. In consideration of TEE being difficult to permanently store data and being vulnerable to attacks, we introduce a (2, 2)-threshold homomorphic cryptosystem to fit the hybrid computation between REE and TEE. Additionally, we carefully design a suite of SOC protocols supporting unary, binary and ternary operations. To achieve applications, we present SEAT, secure data trading based on TRUST. security analysis demonstrates that TRUST enables SOC, avoids collusion attacks among multiple cloud servers, and mitigates potential secret leakage risks within TEE (e.g., from side-channel attacks). Experimental evaluations indicate that TRUST outperforms the state-of-the-art and requires no alignment of data as well as any network communications. Furthermore, SEAT is as effective as the Baseline without any data protection. Copyright © 2024, The Authors. All rights reserved.

关键词： Side channel attack

FedLRDP: Federated Learning Framework with Local Random Differential Privacy

学校读者我要写书评

暂无评论

FedLRDP: Federated Learning Framework with Local Random Diff...

International Joint Conference on Neural networks (IJCNN)

作者： Runtian Zhou Anming Dong Jiguo Yu Qingyan Ding Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Federated learning (FL) is a distributed machine learning framework enabling multiple clients to collaboratively train a shared ML model without sharing raw data. Despite its aim to safeguard data security and privacy, FL faces risks from advanced adversarial attacks like membership inference attack (MIA), potentially leaking sensitive information. To counter these threats, differential privacy (DP) methods add noise to shared model parameters. However, traditional DP methods struggle with balancing model accuracy, training efficiency, and privacy protection, often compromising one for the other. Additionally, uniform DP mechanisms may not cater to varying client privacy and performance needs. To tackle these challenges, we propose a federated learning framework based on localized random differential privacy (FedLRDP). This approach empowers each client to control noise levels based on their privacy requirements, enhancing model performance while preserving data privacy. We further optimize client-side loss functions to enhance model performance. Theoretical analysis establishes the convergence bounds for FedLRDP, demonstrating its superior convergence performance. Experimental results on MNIST reveal that FedLRDP improves model accuracy by 3.28% compared to traditional DP methods while mitigating MIA with a 72.48% lower attack success rate than FedAvg. Moreover, on EMNIST, FedLRDP boosts model accuracy by 7.31% compared to traditional DP methods, maintaining a 59.4% lower attack success rate than FedAvg. These findings underscore FedLRDP’s efficacy in meeting client privacy needs while enhancing model performance.

关键词： Training Differential privacy Privacy Accuracy Federated learning Noise data models

data-Driven Active Power Dispatch for Wind Farms

学校读者我要写书评

暂无评论

Data-Driven Active Power Dispatch for Wind Farms

data Driven Control and Learning Systems (DDCLS)

作者： Xuguo Jiao Daoyuan Zhang Xin Wang Zhaoxing Ma Zhenyong Zhang Wenfeng Liu School of Information and Control Engineering Qingdao University of Technology Qingdao China State Key Laboratory of Industrial Control Technology College of Control Science and Engineering Zhejiang University Hangzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Civil Engineering Qingdao University of Technology Qingdao China

ISBN: (数字)9798350361674

ISBN: (纸本)9798350361681

Active power dispatch of wind farms plays an important role in power grid scheduling. In this paper, a data-driven active power dispatch strategy for wind farms is proposed, which uses the key point of minimizing the standard deviation of wind turbines' output power series to reduce their fluctuations. First, to build the optimization problem, the historical active power output data of each wind turbine is collected from the Supervisory Control And data Acquisition (SCADA) system. Then, the objective function is developed based on the idea of minimizing the standard deviation of the output power time series. Meanwhile, considering the constraints of wind turbines' output power and active power balance of the grid, the feasible domain of the cost function is constructed. Further, to solve the proposed nonlinear optimization problem with equality and inequality constraints, the trust region interior point method (TRIPM) is employed to explore optimal solution within the feasible domain. Finally, actual data collected from wind farms is used to test effectiveness of the designed approach and experimental results show that our method can achieve better output power smoothing performance than conventional Proportional Dispatch (PD) method.

关键词： Fluctuations Time series analysis SCADA systems Power smoothing Wind farms Linear programming Power grids

Identity-aware attribute recognition via real-time distributed inference in mobile edge clouds

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Xu, Zichuan Zhou, Pan Wu, Jiangkai Ren, Jiankang Xia, Qiufen Liang, Huizhi Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province School of Software Dalian University of Technology Dalian China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Software Dalian University of Technology Dalian China School of Computer Science Dalian University of Technology Dalian China Key Laboratory for Ubiquitous Network Service Software of Liaoning Province International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science University of Reading Reading United Kingdom

With the development of deep learning technologies, attribute recognition and person re-identification (re-ID) have attracted extensive attention and achieved continuous improvement via executing computing-intensive deep neural networks in cloud datacenters. However, the datacenter deployment cannot meet the real-time requirement of attribute recognition and person re-ID, due to the prohibitive delay of backhaul networks and large data transmissions from cameras to datacenters. A feasible solution thus is to employ mobile edge clouds (MEC) within the proximity of cameras and enable distributed inference. In this paper, we design novel models for pedestrian attribute recognition with re-ID in an MEC-enabled camera monitoring system. We also investigate the problem of distributed inference in the MEC-enabled camera network. To this end, we first propose a novel inference framework with a set of distributed modules, by jointly considering the attribute recognition and person re-ID. We then devise a learning-based algorithm for the distributions of the modules of the proposed distributed inference framework, considering the dynamic MEC-enabled camera network with uncertainties. We finally evaluate the performance of the proposed algorithm by Copyright © 2020, The Authors. All rights reserved.

关键词： Mobile edge computing

Tensor and Minimum Connected Dominating Set based Confident Information Coverage Reliability Evaluation for IoT

学校读者我要写书评

暂无评论

IEEE Transactions on Sustainable Computing

IEEE Transactions on Sustainable Computing 2024年

作者： Xiao, Ziheng Zhu, Chenlu Feng, Wei Liu, Shenghao Deng, Xianjun Lu, Hongwei Yang, Laurence T. Park, Jong Hyuk 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 Hubei Wuhan430074 China Artificial Intelligence and Intelligent Transportation Joint Technical Center of HUST and Hubei Chutian Intelligent Transportation Company Ltd United States Network and Industrial Control Information Security Technology Department China Nuclear Power Operation Technology Company Ltd. 1011 Xiongchu Avenue Hubei Wuhan430070 China The Department of Computer Science and Engineering Seoul National University of Science and Technology Seoul01811 Korea Republic of

Internet of Things (IoT) reliability evaluation contributes to the sustainable computing and enhanced stability of the network. Previous algorithms usually evaluate the reliability of IoT by enumenating the states of nodes and networks, which are difficult to handle IoT with hundreds of nodes because the computational cost. In this paper, a novel algorithm, TMCRA, is proposed to evaluate the reliability of IoT in complex network environment, which consider both coverage and connectivity. For coverage, TMCRA employs the Confident Information Coverage (CIC) model to divide the target area into independent grids and calculates the coverage rate. In terms of connectivity, TMCRA forming the Virtual Backbone network (VBN) based on two proposed methods: TMA and MGIN, and evaluate connectivity by analyzing the VBN rather than the whole network. The TMA and MGIN are two algorithms for constructing Minimum Connected Dominant Sets (MCDS), which are suitable for different scale networks. Finally, based on the data of coverage and connectivity, TMCRA utilizes tensors for the unified modeling and representation of network structure, and calculates IoT reliability based on the tensors. Simulations are carried out for various sizes of IoT to show the advantages and effectiveness of the proposed approach in reliability evaluation. © 2016 IEEE.

关键词： data reliability