检索结果-南通市图书馆

Model architecture level privacy leakage in neural networks

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 20-32页

作者： Yan LI Hongyang YAN Teng HUANG Zijie PAN Jiewei LAI Xiaoxue ZHANG Kongyang CHEN Jin LI Institute of Artificial Intelligent and Blockchain Guangzhou University Pazhou lab

Privacy leakage is one of the most critical issues in machine learning and has attracted growing interest for tasks such as demonstrating potential threats in model attacks and creating model *** recent years, numerous studies have revealed various privacy leakage risks(e.g., data reconstruction attack, membership inference attack, backdoor attack, and adversarial attack) and several targeted defense approaches(e.g., data denoising, differential privacy, and data encryption). However, existing solutions generally focus on model parameter levels to disclose(or repair) privacy threats during the model training and/or model interference process, which are rarely applied at the model architecture level. Thus, in this paper, we aim to exploit the potential privacy leakage at the model architecture level through a pioneer study on neural architecture search(NAS) paradigms which serves as a powerful tool to automate a neural network *** investigating the NAS procedure, we discover two attack threats in the model architecture level called the architectural dataset reconstruction attack and the architectural membership inference attack. Our theoretical analysis and experimental evaluation reveal that an attacker may leverage the output architecture of an ongoing NAS paradigm to reconstruct its original training set, or accurately infer the memberships of its training set simply from the model architecture. In this work, we also propose several defense approaches related to these model architecture attacks. We hope our work can highlight the need for greater attention to privacy protection in model architecture levels(e.g., NAS paradigms).

关键词： neural architecture search data reconstruction attack membership inference attack

A survey on dynamic graph processing on GPUs: concepts, terminologies and systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Frontiers of Computer Science 2024年第4期18卷 1-23页

作者： Hongru GAO Xiaofei LIAO Zhiyuan SHAO Kexin LI Jiajie CHEN Hai JIN 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 TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang lab Hangzhou 311121China

Graphs that are used to model real-world entities with vertices and relationships among entities with edges,have proven to be a powerful tool for describing real-world problems in *** most real-world scenarios,entities and their relationships are subject to constant *** that record such changes are called dynamic *** recent years,the widespread application scenarios of dynamic graphs have stimulated extensive research on dynamic graph processing systems that continuously ingest graph updates and produce up-to-date graph analytics *** the scale of dynamic graphs becomes larger,higher performance requirements are demanded to dynamic graph processing *** the massive parallel processing power and high memory bandwidth,GPUs become mainstream vehicles to accelerate dynamic graph processing ***-based dynamic graph processing systems mainly address two challenges:maintaining the graph data when updates occur(i.e.,graph updating)and producing analytics results in time(i.e.,graph computing).In this paper,we survey GPU-based dynamic graph processing systems and review their methods on addressing both graph updating and graph *** comprehensively discuss existing dynamic graph processing systems on GPUs,we first introduce the terminologies of dynamic graph processing and then develop a taxonomy to describe the methods employed for graph updating and graph *** addition,we discuss the challenges and future research directions of dynamic graph processing on GPUs.

关键词： dynamic graphs graph processing graph algorithms GPUs

A New Speed Limit Recognition Methodology Based on Ensemble Learning:Hardware Validation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2024年第7期80卷 119-138页

作者： Mohamed Karray Nesrine Triki Mohamed Ksantini ESME ESME Research LabIvry Sur Seine94200France CEM Lab ENISUniversity of SfaxSfax3038Tunisia

Advanced DriverAssistance Systems(ADAS)technologies can assist drivers or be part of automatic driving systems to support the driving process and improve the level of safety and comfort on the *** Sign Recognition System(TSRS)is one of themost important components *** the challengeswith TSRS is being able to recognize road signs with the highest accuracy and the shortest processing ***,this paper introduces a new real time methodology recognizing Speed Limit Signs based on a trio of developed ***,the Speed Limit Detection(SLD)module uses the Haar Cascade technique to generate a new SL detector in order to localize SL signs within captured ***,the Speed Limit Classification(SLC)module,featuring machine learning classifiers alongside a newly developed model called DeepSL,harnesses the power of a CNN architecture to extract intricate features from speed limit sign images,ensuring efficient and precise *** addition,a new Speed Limit Classifiers Fusion(SLCF)module has been developed by combining trained ML classifiers and the DeepSL model by using the Dempster-Shafer theory of belief functions and ensemble learning’s voting *** rigorous software and hardware validation processes,the proposedmethodology has achieved highly significant F1 scores of 99.98%and 99.96%for DS theory and the votingmethod,***,a prototype encompassing all components demonstrates outstanding reliability and efficacy,with processing times of 150 ms for the Raspberry Pi board and 81.5 ms for the Nano Jetson board,marking a significant advancement in TSRS technology.

关键词： Driving automation advanced driver assistance systems(ADAS) traffic sign recognition(TSR) artificial intelligence ensemble learning belief functions voting method

Synthesis and characteristics of transparent Gd_(2)O_(3)ceramics with cubic structure

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Advanced Ceramics 2024年第4期13卷 463-468页

作者： Akio Ikesue Yan Lin Aung World lab Co. Nagoya456-8587Japan

Transparent Gd_(2)O_(3)ceramics with a cubic crystal structure were successfully synthesized for the first *** Gd_(2)O_(3)ceramics subjected to hot isostatic press(HIP)at 1070℃consisted of uniform grains of 2-3μm,and only a few residual pores could be detected inside the materials.X-ray diffraction(XRD)shows that the obtained polycrystalline materials have a cubic crystal structure,and the transmission polarized light observation shows that there is no birefringence inside the materials,indicating inherent optical properties of the cubic crystal *** optical absorption edge is 640 nm(optical band gap:2.1 eV),and the transmittance in the visible to near-infrared region is 72%,which is close to the theoretical transmittance calculated from Fresnel *** constant of this material is almost wavelength-independent,and it is diamagnetic since it has the opposite polarity to that of common paramagnetic materials.

关键词： gadolinium oxide cubic hot isostatic press(HiP) diamagnetic Verdet constant

Unbalanced private set intersection with linear communication complexity

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 79-93页

作者： Quanyu ZHAO Bingbing JIANG Yuan ZHANG Heng WANG Yunlong MAO Sheng ZHONG Department of Computer Science and Technology Nanjing University Purple Mountain lab

The private set intersection(PSI) protocol allows two parties holding a set of integers to compute the intersection of their sets without revealing any additional information to each other. The unbalanced PSI schemes consider a specific setting where a client holds a small set of the size n and a server holds a much larger set of the size m(n ■ m). The communication overhead of state-of-the-art balanced PSI schemes is O(m + n) and the unbalanced PSI schemes are O(nlogm). In this paper, we propose a novel secure unbalanced PSI protocol based on a hash proof system. The communication complexity of our protocol grows only linearly with the size of the small set. In other words, our protocol achieves communication overhead of O(n). We test the performance on a personal computer(PC) machine with a local area network(LAN)setting for the network. The experimental results demonstrate that the client only takes 2.01 s of online computation, 4.27 MB of round trip communication to intersect 1600 pieces of 32-bit integers with 220pieces of 32-bit integers with the security parameter λ = 512. Our protocol is efficient and can be applied to resource-constrained devices, such as cell phones.

关键词： unbalanced private set intersection Hash proof system linear communication complexity small set resource-constrained devices

Distributed Fault-Tolerant Control of Uncertain Multi-Agent Systems with Connectivity Maintenance

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems Science & Complexity 2024年第1期37卷 40-62页

作者： XING Xueyan HU Guoqiang Continental-NTU Corporate lab Nanyang Technological UniversitySingapore 639798Singapore Continental-NTU Corporate lab and the School of Electrical and Electronic Engineering Nanyang Technological UniversitySingapore 639798Singapore

In this paper,a distributed cooperative control protocol is presented to deal with actuator failures of multi-agent systems in the presence of connectivity *** the developed strategy,each agent can track the reference trajectory of the leader in the presence of actuator failures,disturbances and *** connectivity of the multi-agent system can always be ensured during the control *** achieve the aforementioned control objectives,a potential function is introduced to the distributed adaptive fault-tolerant control algorithm to preserve the initial connected network among the *** uncertainty of the multi-agent system,which is allowed to be described by discontinuous functions,is approximated and compensated using the fuzzy logic *** asymptotic stability of the closed-loop system is demonstrated through the use of Cellina’s approximate selection theorem of nonsmooth *** to the developed adaptive laws,the upper bound of the disturbance is allowed to be uncertain,which facilitates the implementation of the control ***,simulation results are provided to verify the effectiveness of the proposed control scheme.

关键词： Actuator failure connectivity maintenance coordination control uncertainties

维普期刊数据库

SeeMore: a spatiotemporal predictive model with bidirectional distillation and level-specific meta-adaptation

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第8期67卷 147-171页

作者： Yuqing MA Wei LIU Yajun GAO Yang YUAN Shihao BAI Haotong QIN Xianglong LIU State Key lab of Software Development Environment Beihang University

Predicting future frames using historical spatiotemporal data sequences is challenging and critical, and it is receiving a lot of attention these days from academic and industrial scholars. Most spatiotemporal predictive algorithms ignore the valuable backward reasoning ability and the disparate learning complexities among different layers and hence, cannot build good long-term dependencies and spatial correlations,resulting in suboptimal solutions. To address the aforementioned issues, we propose a two-stage coarse-to-fine spatiotemporal predictive model with bidirectional distillation and level-specific meta-adaptation(See More)in this paper, which includes a bidirectional distillation network(BDN) and a level-specific meta-adapter(LMA), to gain bidirectional multilevel reasoning. In the first stage, BDN concentrates on bidirectional dynamics modeling and coarsely constructs spatial correlations of different layers, while LMA is introduced in the second fine-tuning stage to refine the multilevel spatial correlations from a meta-learning *** particular, BDN mimics the forward and backward reasoning abilities of humans in a distillation manner,which aids in the development of long-term dependencies. The LMA views learning of different layers as disparate but related tasks and guides the transfer of learning experiences among these tasks through learning complexities. Thus, each layer could be closer to its solutions and could extract more informative spatial correlations. By capturing the enhanced short-term spatial correlations and long-term temporal dependencies,the proposed model could extract adequate knowledge from sequential historical observations and accurately predict future frames whose backtracking preconditions are consistent with the historical sequence. Our work is general and robust enough to be integrated into most spatiotemporal predictive models without requiring additional computation or memory cost during inference. Extensive experimen

关键词： spatiotemporal predictive learning knowledge transfer bidirectional distillation network level-specific meta-adapter coarse-to-fine training

Resilience assessment and optimization method of city road network in the post-earthquake emergency period

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Earthquake Engineering and Engineering Vibration 2024年第3期23卷 765-779页

作者： Wang Haoran Xiao Jia Li Shuang Zhai Changhai Key lab of Structures Dynamic Behavior and Control of the Ministry of Education Key Lab of Smart Prevention and Mitigation of Civil Engineering Disasters of the Ministry of Industry and Information TechnologyHarbin Institute of TechnologyHarbin 150090China

The post-earthquake emergency period,which is a sensitive time segment just after an event,mainly focuses on saving life and restoring social *** improve the seismic resilience of city road networks,a resilience evaluation method used in the post-earthquake emergency period is *** road seismic damage index of a city road network can consider the influence of roads,bridges and buildings along the roads,*** road capacity after an earthquake.A function index for a city road network is developed,which reflects the connectivity,redundancy,traffic demand and traffic function of the *** optimization model for improving the road repair order in the post-earthquake emergency period is also developed according to the resilience evaluation,to enable decision support for city emergency management and achieve the best seismic resilience of the city road *** optimization model is applied to a city road network and the results illustrate the feasibility of the resilience evaluation and optimization method for a city road network in the post-earthquake emergency period.

关键词： city road network post-earthquake emergency period traffic demand resilience evaluation optimization model

维普期刊数据库

Interference mitigation and target detection for automotive FMCW radar with range-Doppler sparse regularization

在线全文

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第9期67卷 342-343页

作者： Yan HUANG Yunxuan WANG Xiao ZHOU Hui ZHANG Yuan MAO Guisheng LIAO Wei HONG State Key lab of Millimeter Waves Southeast University Department of Computer Science University College London National Key lab of Radar Signal Processing Xidian University

The invention of vehicles has shaped our modern society and accelerated our economy while causing many tragic incidents simultaneously. Some advanced driver-assistance systems(ADAS) based on surrounding environment se... 详细信息

关键词： Radar interference