检索结果-南通市图书馆

Model architecture level privacy leakage in neural networks

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 defenses.In 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 design.By 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

来源：

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Capturability-based Fuzzy Footstep Planner for a Biped Robot with Centroidal Compliance

引用

Journal of Bionic Engineering 2024年第1期21卷 84-100页

作者： Zihan Xu Qin Fang Yong Ren Chengju Liu Robot and artificial Intelligence lab(RAIL) College of Electronic and Information EngineeringTongji UniversityShanghai 201804China Applied Technology College Soochow UniversitySuzhou 215000China

Compliance motion and footstep adjustment are active balance control strategies from learning human subconscious behaviors.The force estimation without direct end-actuator force measurement and the optimal footsteps based on complex analytical calculation are still challenging tasks for elementary and kid-size position-controlled robots.In this paper,an online compliant controller with Gravity Projection Observer(GPO),which can express the external force condition of perturbations by the estimated Projection of Gravity(PoG)with estimation covariance,is proposed for the realization of disturbance absorption,with which the robustness of the humanoid contact with environments can be maintained.The fuzzy footstep planner based on capturability analysis is proposed,and the Model Predictive Control(MPC)is applied to generate the desired steps.The fuzzification rules are well-designed and give the corresponding control output responding to complex and changeable external disturbances.To validate the presented methods,a series of experiments on a real humanoid robot are conducted.The results verify the effectiveness of the proposed balance control framework.

关键词： Biped walking Centroidal compliance Gravity projection observer Fuzzy footstep planner

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Cognitive-emotional feasibility of the effect of visual quality of building form on promoting the sense of place attachment(Case study:Cultural iconic buildings of Iran’s contemporary architecture)

引用

Frontiers of Architectural Research 2024年第1期13卷 37-56页

作者： Narmin Ariannia Negar Naseri Mansour Yeganeh Digital Architecture and artificial Intelligence lab Department of ArchitectureTarbiat Modares UniversityTehranIran Architectural Design Modeling and Fabrication LabDepartment of ArchitectureTarbiat Modares UniversityTehranIran

The present research studies the relationship between place attachment and the perception of form’s visual quality in fifteen outstanding contemporary Iranian architectural cultural buildings.This study puts forward the hypothesis that there is a correlation between the quality of building form and the sense of place attachment,in the sense that creating high visual quality through enhancing the quality of building form increases citizens’initial satisfaction with and subsequent attachment to the building.High visual quality influences people’s experience of the environment and improves the quality of life.Place attachment highlights how people,on a personal level,recreate a sense of place for themselves.The present study adopts the descriptive-analytical method as its theoretical framework and the survey as the empirical methodology.Questionnaires were developed using the Likert scale and distributed among experts and ordinary citizens.Data analysis using SPSS and the adoption of descriptive-analytical statistics,correlation analysis,and regression showed the relationship among the characteristics of indicators.The results show a positive correlation between form and place attachment mediated through visual quality,and they are causal conditions for one another.In addition,only some of the buildings under study evoke the same level of place attachment.

关键词： Visual preferences Environmental quality Environmental psychology Mental schemas Contemporary architecture

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Astronomical Knowledge Entity Extraction in Astrophysics Journal Articles via Large Language Models

引用

Research in Astronomy and Astrophysics 2024年第6期24卷 142-157页

作者： Wujun Shao Rui Zhang Pengli Ji Dongwei Fan Yaohua Hu Xiaoran Yan Chenzhou Cui Yihan Tao Linying Mi Lang Chen National Astronomical Observatories Chinese Academy of Sciences University of Chinese Academy of Sciences National Astronomical Data Center Research Institute of artificial Intelligence Zhejiang Lab Guilin University Xidian University

Astronomical knowledge entities, such as celestial object identifiers, are crucial for literature retrieval and knowledge graph construction, and other research and applications in the field of astronomy. Traditional methods of extracting knowledge entities from texts face numerous challenging obstacles that are difficult to overcome.Consequently, there is a pressing need for improved methods to efficiently extract them. This study explores the potential of pre-trained Large Language Models(LLMs) to perform astronomical knowledge entity extraction(KEE) task from astrophysical journal articles using prompts. We propose a prompting strategy called PromptKEE, which includes five prompt elements, and design eight combination prompts based on them. We select four representative LLMs(Llama-2-70B, GPT-3.5, GPT-4, and Claude 2) and attempt to extract the most typical astronomical knowledge entities, celestial object identifiers and telescope names, from astronomical journal articles using these eight combination prompts. To accommodate their token limitations, we construct two data sets: the full texts and paragraph collections of 30 articles. Leveraging the eight prompts, we test on full texts with GPT-4and Claude 2, on paragraph collections with all LLMs. The experimental results demonstrate that pre-trained LLMs show significant potential in performing KEE tasks, but their performance varies on the two data sets. Furthermore,we analyze some important factors that influence the performance of LLMs in entity extraction and provide insights for future KEE tasks in astrophysical articles using LLMs. Finally, compared to other methods of KEE,LLMs exhibit strong competitiveness in multiple aspects.

关键词： astronomical databases: miscellaneous methods: data analysis virtual observatory tools

来源：

同方期刊数据库评论

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 study of lithographic variation in resistive random access memory

引用

Journal of Semiconductors 2024年第5期45卷 69-79页

作者： Yuhang Zhang Guanghui He Feng Zhang Yongfu Li Guoxing Wang Department of Micro-Nano Electronics Shanghai Jiao Tong UniversityShanghai 200240China MoE Key lab of artificial Intelligence Shanghai Jiao Tong UniversityShanghai 200240China Institute of Microelectronics Chinese Academy of SciencesBeijing 100029China

Reducing the process variation is a significant concern for resistive random access memory(RRAM).Due to its ultrahigh integration density,RRAM arrays are prone to lithographic variation during the lithography process,introducing electrical variation among different RRAM devices.In this work,an optical physical verification methodology for the RRAM array is developed,and the effects of different layout parameters on important electrical characteristics are systematically investigated.The results indicate that the RRAM devices can be categorized into three clusters according to their locations and lithography environments.The read resistance is more sensitive to the locations in the array(~30%)than SET/RESET voltage(<10%).The increase in the RRAM device length and the application of the optical proximity correction technique can help to reduce the variation to less than 10%,whereas it reduces RRAM read resistance by 4×,resulting in a higher power and area consumption.As such,we provide design guidelines to minimize the electrical variation of RRAM arrays due to the lithography process.

关键词： layout lithography process variation resistive random access memory

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

An anti-collision algorithm for robotic search-and-rescue tasks in unknown dynamic environments

引用

Frontiers of Information Technology & Electronic Engineering 2024年第4期25卷 569-584页

作者： Yang CHEN Dianxi SHI Huanhuan YANG Tongyue LI Zhen WANG School of Computer Science Peking UniversityBeijing 100871China Tianjin artificial Intelligence Innovation Center Tianjin 300457China Intelligent Game and Decision lab Beijing 100071China College of Computer National University of Defense TechnologyChangsha 410073China

This paper deals with the search-and-rescue tasks of a mobile robot with multiple interesting targets in an unknown dynamic environment.The problem is challenging because the mobile robot needs to search for multiple targets while avoiding obstacles simultaneously.To ensure that the mobile robot avoids obstacles properly,we propose a mixed-strategy Nash equilibrium based Dyna-Q(MNDQ)algorithm.First,a multi-objective layered structure is introduced to simplify the representation of multiple objectives and reduce computational complexity.This structure divides the overall task into subtasks,including searching for targets and avoiding obstacles.Second,a risk-monitoring mechanism is proposed based on the relative positions of dynamic risks.This mechanism helps the robot avoid potential collisions and unnecessary detours.Then,to improve sampling efficiency,MNDQ is presented,which combines Dyna-Q and mixed-strategy Nash equilibrium.By using mixed-strategy Nash equilibrium,the agent makes decisions in the form of probabilities,maximizing the expected rewards and improving the overall performance of the Dyna-Q algorithm.Furthermore,a series of simulations are conducted to verify the effectiveness of the proposed method.The results show that MNDQ performs well and exhibits robustness,providing a competitive solution for future autonomous robot navigation tasks.

关键词： Search and rescue Reinforcement learning Game theory Collision avoidance Decision-making

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

SinGRAV: Learning a Generative Radiance Volume from a Single Natural Scene

引用

Journal of Computer Science & Technology 2024年第2期39卷 305-319页

作者：王玉洁陈学霖陈宝权 School of Computer Science and Technology Shandong UniversityQingdao 266237China State Key laboratory of General artificial Intelligence Beijing 100871China School of Intelligence Science and Technology Peking UniversityBeijing 100871China Tencent AI lab Tencent Holdings LimitedShenzhen 518057China

We present SinGRAV, an attempt to learn a generative radiance volume from multi-view observations of a single natural scene, in stark contrast to existing category-level 3D generative models that learn from images of many object-centric scenes. Inspired by SinGAN, we also learn the internal distribution of the input scene, which necessitates our key designs w.r.t. the scene representation and network architecture. Unlike popular multi-layer perceptrons (MLP)-based architectures, we particularly employ convolutional generators and discriminators, which inherently possess spatial locality bias, to operate over voxelized volumes for learning the internal distribution over a plethora of overlapping regions. On the other hand, localizing the adversarial generators and discriminators over confined areas with limited receptive fields easily leads to highly implausible geometric structures in the spatial. Our remedy is to use spatial inductive bias and joint discrimination on geometric clues in the form of 2D depth maps. This strategy is effective in improving spatial arrangement while incurring negligible additional computational cost. Experimental results demonstrate the ability of SinGRAV in generating plausible and diverse variations from a single scene, the merits of SinGRAV over state-of-the-art generative neural scene models, and the versatility of SinGRAV by its use in a variety of applications. Code and data will be released to facilitate further research.

关键词： generative model neural radiance field 3D scene generation

来源：

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Ferroptosis inhibitors reduce celastrol toxicity and preserve its insulin sensitizing effects in insulin resistant HepG2 cells

引用

Journal of Integrative Medicine 2024年第3期22卷 286-294页

作者： Jia-jia Liu Xue Zhang Bang-lan Cai Man-man Qi Yong-bin Chi Bin Peng Deng-hai Zhang School of Medicine Shanghai UniversityShanghai 200444China Shanghai Health Commission Key lab of artificial Intelligence-Based Management of Inflammation and Chronic Diseases Shanghai Pudong Gongli HospitalSecondary Military Medical UniversityShanghai 200135China School of Basic Medicine Ningxia Medical UniversityYinchuan 750004Ningxia Hui Autonomous RegionChina

Objective:Research has shown that celastrol can effectively treat a variety of diseases,yet when passing a certain dosage threshold,celastrol becomes toxic,causing complications such as liver and kidney damage and erythrocytopenia,among others.With this dichotomy in mind,it is extremely important to find ways to preserve celastrol’s efficacy while reducing or preventing its toxicity.Methods:In this study,insulin-resistant Hep G2(IR-Hep G2)cells were prepared using palmitic acid and used for in vitro experiments.IR-Hep G2 cells were treated with celastrol alone or in combination with Nacetylcysteine(NAC)or ferrostatin-1(Fer-1)for 12,24 or 48 h,at a range of doses.Cell counting kit-8assay,Western blotting,quantitative reverse transcription-polymerase chain reaction,glucose consumption assessment,and flow cytometry were performed to measure celastrol’s cytotoxicity and whether the cell death was linked to ferroptosis.Results:Celastrol treatment increased lipid oxidation and decreased expression of anti-ferroptosis proteins in IR-Hep G2 cells.Celastrol downregulated glutathione peroxidase 4(GPX4)m RNA.Molecular docking models predicted that solute carrier family 7 member 11(SLC7A11)and GPX4 were covalently bound by celastrol.Importantly,we found for the first time that the application of ferroptosis inhibitors(especially NAC)was able to reduce celastrol’s toxicity while preserving its ability to improve insulin sensitivity in IR-Hep G2 cells.Conclusion:One potential mechanism of celastrol’s cytotoxicity is the induction of ferroptosis,which can be alleviated by treatment with ferroptosis inhibitors.These findings provide a new strategy to block celastrol’s toxicity while preserving its therapeutic effects.

关键词： Celastrol Insulin resistance Ferroptosis N-Acetylcysteine Palmitic acid Molecular docking

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

3D bioprinting of in vitro porous hepatoma models:establishment,evaluation,and anticancer drug testing

引用

Bio-Design and Manufacturing 2024年第2期7卷 137-152页

作者： Xiaoyuan Wang Zixian Liu Qianqian Duan Boye Zhang Yanyan Cao Zhizhong Shen Meng Li Yanfeng Xi Jianming Wang Shengbo Sang Shanxi Key laboratory of Micro Nano Sensors and artificial Intelligence Perception College of Electronic Information and Optical EngineeringTaiyuan University of TechnologyTaiyuan 030024China Key lab of Advanced Transducers and Intelligent Control System of the Ministry of Education Taiyuan University of TechnologyTaiyuan 030024China Shanxi Institute of 6D artificial Intelligence Biomedical Science Taiyuan 030031China Shanxi-Zheda Institute of Advanced Materials and Chemical Engineering Taiyuan 030024China Department of Pathology Shanxi Provincial Cancer HospitalTaiyuan 030024China General Hospital of Taiyuan Iron and Steel Company Taiyuan 030809China

Traditional tumor models do not tend to accurately simulate tumor growth in vitro or enable personalized treatment and are particularly unable to discover more beneficial targeted drugs.To address this,this study describes the use of threedimensional(3D)bioprinting technology to construct a 3D model with human hepatocarcinoma SMMC-7721 cells(3DP-7721)by combining gelatin methacrylate(GelMA)and poly(ethylene oxide)(PEO)as two immiscible aqueous phases to form a bioink and innovatively applying fluorescent carbon quantum dots for long-term tracking of cells.The GelMA(10%,mass fraction)and PEO(1.6%,mass fraction)hydrogel with 3:1 volume ratio offered distinct pore-forming characteristics,satisfactorymechanical properties,and biocompatibility for the creation of the 3DP-7721 model.Immunofluorescence analysis and quantitative real-time fluorescence polymerase chain reaction(PCR)were used to evaluate the biological properties of the model.Compared with the two-dimensional culture cell model(2D-7721)and the 3D mixed culture cell model(3DM-7721),3DP-7721 significantly improved the proliferation of cells and expression of tumor-related proteins and genes.Moreover,we evaluated the differences between the three culture models and the effectiveness of antitumor drugs in the three models and discovered that the efficacy of antitumor drugs varied because of significant differences in resistance proteins and genes between the three models.In addition,the comparison of tumor formation in the three models found that the cells cultured by the 3DP-7721 model had strong tumorigenicity in nude mice.Immunohistochemical evaluation of the levels of biochemical indicators related to the formation of solid tumors showed that the 3DP-7721 model group exhibited pathological characteristics of malignant tumors,the generated solid tumors were similar to actual tumors,and the deterioration was higher.This research therefore acts as a foundation for the application of 3DP-7721 models in drug development research.

关键词： 3D bioprinting Hepatoma tumor models Drug screening Antitumor drug development

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

Data-driven discovery of linear dynamical systems from noisy data

引用

Science China(Technological Sciences) 2024年第1期67卷 121-129页

作者： WANG YaSen YUAN Ye FANG HuaZhen DING Han School of Mechanical Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China State Key lab of Digital Manufacturing Equipment and Technology Huazhong University of Science and TechnologyWuhan 430074China School of artificial Intelligence and Automation Huazhong University of Science and TechnologyWuhan 430074China Department of Mechanical Engineering University of KansasLawrence 66045USA

In modern science and engineering disciplines,data-driven discovery methods play a fundamental role in system modeling,as data serve as the external representations of the intrinsic mechanisms within systems.However,empirical data contaminated by process and measurement noise remain a significant obstacle for this type of modeling.In this study,we have developed a data-driven method capable of directly uncovering linear dynamical systems from noisy data.This method combines the Kalman smoothing and sparse Bayesian learning to decouple process and measurement noise under the expectation-maximization framework,presenting an analytical method for alternate state estimation and system identification.Furthermore,the discovered model explicitly characterizes the probability distribution of process and measurement noise,as they are essential for filtering,smoothing,and stochastic control.We have successfully applied the proposed algorithm to several simulation systems.Experimental results demonstrate its potential to enable linear dynamical system discovery in practical applications where noise-free data are intractable to capture.

关键词： system identification sparse Bayesian learning Kalman smoothing process and measurement noise

来源：

维普期刊数据库

同方期刊数据库评论

在线全文

学校读者我要写书评

暂无评论

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

请选择保存的检索档案：

请选择收藏分类：

通借通还

欢迎您,

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

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

在线全文

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：