检索结果-南通市图书馆

维普期刊数据库

Fast Cross-Platform Binary Code Similarity Detection Framework Based on CFGs Taking Advantage of NLP and Inductive GNN

在线全文

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 128-138页

作者： Jinxue PENG Yong WANG Jingfeng XUE Zhenyan LIU School of computer Science and technology Beijing Institute of Technology

Cross-platform binary code similarity detection aims at detecting whether two or more pieces of binary code are similar or not. Existing approaches that combine control flow graphs(CFGs)-based function representation and graph convolutional network(GCN)-based similarity analysis are the best-performing ones. Due to a large amount of convolutional computation and the loss of structural information, the use of convolution networks will inevitably bring problems such as high overhead and sometimes inaccuracy. To address these issues, we propose a fast cross-platform binary code similarity detection framework that takes advantage of natural language processing(NLP)and inductive graph neural network(GNN) for basic blocks embedding and function representation respectively by simulating extracting structural features and temporal features. GNN’s node-centric and small batch is a suitable training way for large CFGs, it can greatly reduce computational overhead. Various NLP basic block embedding models and GNNs are evaluated. Experimental results show that the scheme with long short term memory(LSTM)for basic blocks embedding and inductive learning-based Graph SAGE(GAE) for function representation outperforms the state-of-the-art works. In our framework, we can take only 45% overhead. Improve efficiency significantly with a small performance trade-off.

关键词： Control flow graph Natural language processing Inductive graph neural network Binary code similarity detection

Deep Guided Attention Network for Joint Denoising and Demosaicing in Real Image

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electronics 2024年第1期33卷 303-312页

作者： Tao ZHANG Ying FU Jun ZHANG School of computer Science and technology Beijing Institute of Technology Advanced Reasearch institute of Multidisciplinary Science Beijing Institute of Technology

Denoising(DN) and demosaicing(DM) are the first crucial stages in the image signal processing pipeline. Recently, researches pay more attention to solve DN and DM in a joint manner, which is an extremely undetermined inverse problem. Existing deep learning methods learn the desired prior on synthetic dataset, which limits the generalization of learned network to the real world data. Moreover, existing methods mainly focus on the raw data property of high green information sampling rate for DM, but occasionally exploit the high intensity and signalto-noise(SNR) of green channel. In this work, a deep guided attention network(DGAN) is presented for real image joint DN and DM(JDD), which considers both high SNR and high sampling rate of green information for DN and DM, respectively. To ease the training and fully exploit the data property of green channel, we first train DN and DM sub-networks sequentially and then learn them jointly, which can alleviate the error accumulation. Besides, in order to support the real image JDD, we collect paired raw clean RGB and noisy mosaic images to conduct a realistic dataset. The experimental results on real JDD dataset show the presented approach performs better than the state-of-the-art methods, in terms of both quantitative metrics and qualitative visualization.

关键词： Image denoising Image demosaicing Joint processing Guided attention Paired real dataset

A survey on causal inference for recommendation

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

The Innovation 2024年第2期5卷 130-144页

作者： Huishi Luo Fuzhen Zhuang Ruobing Xie Hengshu Zhu Deqing Wang Zhulin An Yongjun Xu institute of Artificial Intelligence Beihang UniversityBeijing 100191China Zhongguancun Laboratory Beijing 100094China WeChat Search application Department TencentBeijing 100080China The Career Science Laboratory BOSS ZhipinBeijing 100028China SKLSDE School of Computer ScienceBeihang UniversityBeijing 100191China institute of Computing technology Chinese Academy of SciencesBeijing 100190China

Causal inference has recently garnered significant interest among recommender system(RS)researchers due to its ability to dissect cause-and-effect relationships and its broad applicability across multiple fields.It offers a framework to model the causality in RSs such as confounding effects and deal with counterfactual problems such as offline policy evaluation and data augmentation.Although there are already some valuable surveys on causal recommendations,they typically classify approaches based on the practical issues faced in RS,a classification that may disperse and fragment the uni-fied causal theories.Considering RS researchers’unfamiliarity with causality,it is necessary yet challenging to comprehensively review relevant studies from a coherent causal theoretical perspective,thereby facilitating a deeper integration of causal inference in RS.This survey provides a systematic review of up-to-date papers in this area from a causal theory standpoint and traces the evolutionary development of RS methods within the same causal strategy.First,we introduce the fundamental concepts of causal inference as the basis of the following review.Subsequently,we propose a novel theory-driven taxonomy,categorizing existing methods based on the causal theory employed,namely those based on the potential outcome framework,the structural causal model,and general counterfactuals.The review then delves into the technical details of how existing methods apply causal inference to address particular recommender issues.Finally,we highlight some promising directions for future research in this field.Representative papers and open-source resources will be progressively available at https://***/Chrissie-Law/Causal-Inference-forRecommendation.

关键词： survey details causal

A Survey on Blockchain-Based Federated Learning:Categorization,application and Analysis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computer Modeling in Engineering & Sciences 2024年第6期139卷 2451-2477页

作者： Yuming Tang Yitian Zhang Tao Niu Zhen Li Zijian Zhang Huaping Chen Long Zhang School of Cyberspace Science&technology Beijing Institute of TechnologyBeijing100081China School of computer Science&technology Beijing Institute of TechnologyBeijing100081China Southeast institute of Information technology Beijing Institute of TechnologyPutian351100China Qianxin technology Group Co. Ltd.Beijing100044China

Federated Learning(FL),as an emergent paradigm in privacy-preserving machine learning,has garnered significant interest from scholars and engineers across both academic and industrial spheres.Despite its innovative approach to model training across distributed networks,FL has its vulnerabilities;the centralized server-client architecture introduces risks of single-point failures.Moreover,the integrity of the global model—a cornerstone of FL—is susceptible to compromise through poisoning attacks by malicious actors.Such attacks and the potential for privacy leakage via inference starkly undermine FL’s foundational privacy and security goals.For these reasons,some participants unwilling use their private data to train a model,which is a bottleneck in the development and industrialization of federated learning.Blockchain technology,characterized by its decentralized ledger system,offers a compelling solution to these issues.It inherently prevents single-point failures and,through its incentive mechanisms,motivates participants to contribute computing power.Thus,blockchain-based FL(BCFL)emerges as a natural progression to address FL’s challenges.This study begins with concise introductions to federated learning and blockchain technologies,followed by a formal analysis of the specific problems that FL encounters.It discusses the challenges of combining the two technologies and presents an overview of the latest cryptographic solutions that prevent privacy leakage during communication and incentives in BCFL.In addition,this research examines the use of BCFL in various fields,such as the Internet of Things and the Internet of Vehicles.Finally,it assesses the effectiveness of these solutions.

关键词： Federated learning blockchain privacy-preserving

A deep learning model enabled multi-event recognition for distributed optical fiber sensing

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第3期67卷 291-307页

作者： Yujiao LI Xiaomin CAO Wenhao NI Kuanglu YU institute of Information Science School of Computer and Information TechnologyBeijing Jiaotong University beijing Key Laboratory of Advanced Information Science and Network technology Beijing Jiaotong University

Fiber optic sensors that utilize backscattered light offer distributed real-time measurements and have been seen tremendous improvements in sensing distance and spatial resolution over the last decades.However, these improvements in sensor capabilities lead to a significant increase in the amount of data that needs to be processed. Traditional processing schemes are no longer adequate, so the development of novel signal processing methods is critical. Phase-sensitive optical time domain reflectometry(Φ-OTDR) is now applied in various applications for multi-event recognition, and it would usually be difficult, sometimes even unrealistic to label all the acquired samples due to its real-time and seamless monitoring nature. To fully take advantage of the information contained within the large number of unlabeled samples, which were formerly not utilized and hence wasted, we propose a semi-supervised model to boost the event classification performance of Φ-OTDR. The model extracts respectively the temporal features and the spatial bidirectional features together with a dual attention mechanism. Its classification accuracy has been improved up to 96.9%with only 1230 labeled samples. In addition, our model shows significant advantages when the number of labeled samples is reduced. Importantly, our method improves the accuracy of multi-event classification without any modification to the optical setup.

关键词： $\Phi$-OTDR event recognition semi-supervised learning mean teacher MT-ACNN-SA-BiLSTM

Pupillometry Analysis of Rapid Serial Visual Presentation at Five Presentation Rates

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and technology 2024年第2期29卷 543-552页

作者： Xi Luo Yanfei Lin Rongxiao Guo Xirui Zhao Shangen Zhang Xiaorong Gao School of Integrated Circuits and Electronics Beijing Institute of TechnologyBeijing 100081China School of computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China School of Medicine Tsinghua UniversityBeijing 100084China

In this study,the effect of presentation rates on pupil dilation is investigated for target recognition in the Rapid Serial Visual Presentation(RSVP)paradigm.In this experiment,the RSVP paradigm with five different presentation rates,including 50,80,100,150,and 200 ms,is designed.The pupillometry data of 15 subjects are collected and analyzed.The pupillometry results reveal that the peak and average amplitudes for pupil size and velocity at the 80-ms presentation rate are considerably higher than those at other presentation rates.The average amplitude of pupil acceleration at the 80-ms presentation rate is significantly higher than those at the other presentation rates.The latencies under 50-and 80-ms presentation rates are considerably lower than those of 100-,150-,and 200-ms presentation rates.Additionally,no considerable differences are observed in the peak,average amplitude,and latency of pupil size,pupil velocity,and acceleration under 100-,150-,and 200-ms presentation rates.These results reveal that with the increase in the presentation rate,pupil dilation first increases,then decreases,and later reaches saturation.The 80-ms presentation rate results in the largest point of pupil dilation.No correlation is observed between pupil dilation and recognition accuracy under the five presentation rates.

关键词： pupil dilation presentation rate Rapid Serial Visual Presentation(RSVP)

Industry-Oriented Detection Method of PCBA Defects Using Semantic Segmentation Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

IEEE/CAA Journal of Automatica Sinica 2024年第6期11卷 1438-1446页

作者： Yang Li Xiao Wang Zhifan He Ze Wang Ke Cheng Sanchuan Ding Yijing Fan Xiaotao Li Yawen Niu Shanpeng Xiao Zhenqi Hao Bin Gao Huaqiang Wu Department of Internet of Things technology and application China Mobile Research InstituteBeijing 100053China beijing Advanced Innovation Center for Integrated Circuits the School of Integrated CircuitTsinghua UniversityBeijing 100084China SigmaStar technology Limited Xiamen 361199China IEEE

Automated optical inspection(AOI)is a significant process in printed circuit board assembly(PCBA)production lines which aims to detect tiny defects in PCBAs.Existing AOI equipment has several deficiencies including low throughput,large computation cost,high latency,and poor flexibility,which limits the efficiency of online PCBA inspection.In this paper,a novel PCBA defect detection method based on a lightweight deep convolution neural network is proposed.In this method,the semantic segmentation model is combined with a rule-based defect recognition algorithm to build up a defect detection frame-work.To improve the performance of the model,extensive real PCBA images are collected from production lines as datasets.Some optimization methods have been applied in the model according to production demand and enable integration in lightweight computing devices.Experiment results show that the production line using our method realizes a throughput more than three times higher than traditional methods.Our method can be integrated into a lightweight inference system and pro-mote the flexibility of AOI.The proposed method builds up a general paradigm and excellent example for model design and optimization oriented towards industrial requirements.

关键词： Automated optical inspection(AOI) deep learning defect detection printed circuit board assembly(PCBA) semantic segmentation.

维普期刊数据库博看期刊

Endogenous Security Formal Definition,Innovation Mechanisms,and Experiment Research in Industrial Internet

在线全文

学校读者我要写书评

暂无评论

Tsinghua Science and technology 2024年第2期29卷 492-505页

作者： Hongsong Chen Xintong Han Yiying Zhang School of computer and Communication Engineering University of Science and Technology BeijingBeijing 100083China

With the rapid development of information technologies,industrial Internet has become more open,and security issues have become more challenging.The endogenous security mechanism can achieve the autonomous immune mechanism without prior knowledge.However,endogenous security lacks a scientific and formal definition in industrial Internet.Therefore,firstly we give a formal definition of endogenous security in industrial Internet and propose a new industrial Internet endogenous security architecture with cost analysis.Secondly,the endogenous security innovation mechanism is clearly defined.Thirdly,an improved clone selection algorithm based on federated learning is proposed.Then,we analyze the threat model of the industrial Internet identity authentication scenario,and propose cross-domain authentication mechanism based on endogenous key and zero-knowledge proof.We conduct identity authentication experiments based on two types of blockchains and compare their experimental results.Based on the experimental analysis,Ethereum alliance blockchain can be used to provide the identity resolution services on the industrial *** of Things application(IOTA)public blockchain can be used for data aggregation analysis of Internet of Things(IoT)edge nodes.Finally,we propose three core challenges and solutions of endogenous security in industrial Internet and give future development directions.

关键词： industrial Internet endogenous security architecture federated learning blockchain

Perspective on powder technology for all-solid-state batteries:How to pair sulfide electrolyte with high-voltage cathode

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Particuology 2024年第3期86卷 55-66页

作者： Jiangkui Hu Shijie Yang Yingying Pei Xilong Wang Yulong Liao Shuai Li Aolong Yue Jia-Qi Huang Hong Yuan School of Materials Science&Engineering Beijing Institute of TechnologyBeijing100081China Advanced Research institute of Multidisciplinary Science Beijing Institute of TechnologyBeijing100081China

Sulfide solid electrolytes(SEs)have attracted ever-increasing attention due to their superior roomtemperature ionic conductivity(~10^(-2) S cm^(-1)).Additionally,the integration of sulfide SEs and highvoltage cathodes is promising to achieve higher energy density.However,the incompatible interfaces between sulfide SEs and high-voltage cathodes have been one of the key factors limiting their applications.Therefore,this review presents a critical summarization of the interfacial issues in all-solid-state lithium batteries based on sulfide SEs and high-voltage cathodes and proposes strategies to stabilize the electrolyte/cathode interfaces.Moreover,the future research direction of electrolyte/cathode interfaces and application prospects of powder technology in sulfide-based ASSLBs were also discussed.

关键词： Sulfide solid electrolytes High-voltage cathodes Electrode/electrolyte interfaces All-solid-state lithium batteries