检索结果-内蒙古大学图书馆

8th International Conference on Data science in Cyberspace, DSC 2023

作者： Li, Hu Ma, Qiongmin Zhang, Ming Kuang, Xiaohui National Key Laboratory of Science and Technology on Information System Security Beijing China National Key Laboratory for Complex Systems Simulation Beijing China

ISBN: (纸本)9798350331035

Machine Learning and Artificial Intelligence technology accelerates technological progress and promotes social development, but also brings many security problems. Machine learning models may be affected, deceived, controlled or destroyed at different stages, e.g. training and inference, which may lead to serious consequences. In view of the main stages of the life cycle of machine learning, we summarizes the related attack and defense technologies based on threat matrix, makes a comprehensive and systematic analysis on the security issues of machine learning, and puts forward several security protection suggestions for intelligent information systems. © 2023 IEEE.

关键词： Artificial Intelligence Machine Learning Security Analysis Threat Matrix

来源：评论

学校读者我要写书评

暂无评论

ALARM: Align Language Models via Hierarchical Rewards Modeling 62

ALARM: Align Language Models via Hierarchical Rewards Modeli...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Lai, Yuhang Wang, Siyuan Liu, Shujun Huang, Xuanjing Wei, Zhongyu Institute of Science and Technology for Brain-inspired Intelligence Fudan University China School of Data Science Fudan University China School of Computer Science Fudan University China Research Institute of Intelligent and Complex Systems Fudan University China

ISBN: (纸本)9798891760998

We introduce ALARM, the first framework modeling hierarchical rewards in reinforcement learning from human feedback (RLHF), which is designed to enhance the alignment of large language models (LLMs) with human preferences. The framework addresses the limitations of current alignment approaches, which often struggle with the inconsistency and sparsity of human supervision signals, by integrating holistic rewards with aspect-specific rewards. This integration enables more precise and consistent guidance of language models towards desired outcomes, particularly in complex and open text generation tasks. By employing a methodology that filters and combines multiple rewards based on their consistency, the framework provides a reliable mechanism for improving model alignment. We validate our approach through applications in long-form question answering and machine translation tasks, employing gpt-3.5-turbo for pairwise comparisons, and demonstrate improvements over existing baselines. Our work underscores the effectiveness of hierarchical rewards modeling in refining LLM training processes for better human preference alignment. We release our code at https://***. © 2024 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Network Security Situation Prediction Based on TCAN-BiGRU Optimized by SSA and IQPSO

引用

Computer systems science & Engineering 2023年第10期47卷 993-1021页

作者： Junfeng Sun Chenghai Li Yafei Song Peng Ni Jian Wang College of Air and Missile Defence Air Force Engineering UniversityXi’an710051China Science and Technology on Complex Aviation Systems Simulation Laboratory Beijing100076China

The accuracy of historical situation values is required for traditional network security situation prediction(NSSP).There are discrepancies in the correlation and weighting of the various network security *** solve these problems,a combined prediction model based on the temporal convolution attention network(TCAN)and bi-directional gate recurrent unit(BiGRU)network is proposed,which is optimized by singular spectrum analysis(SSA)and improved quantum particle swarmoptimization algorithm(IQPSO).This model first decomposes and reconstructs network security situation data into a series of subsequences by SSA to remove the noise from the ***,a prediction model of TCAN-BiGRU is established respectively for each *** uses the TCN to extract features from the network security situation data and the improved channel attention mechanism(CAM)to extract important feature information from *** learns the before-after status of situation data to extract more feature information from sequences for ***,IQPSO is proposed to optimize the hyperparameters of ***,the prediction results of the subsequence are superimposed to obtain the final predicted *** the one hand,IQPSO compares with other optimization algorithms in the experiment,whose performance can find the optimum value of the benchmark function many times,showing that IQPSO performs *** the other hand,the established prediction model compares with the traditional prediction methods through the simulation experiment,whose coefficient of determination is up to 0.999 on both sets,indicating that the combined prediction model established has higher prediction accuracy.

关键词： Network security situation prediction SSA IQPSO TCAN-BiGRU

来源：评论

学校读者我要写书评

暂无评论

Design of Recursive Filtering Scheme via An Improved Weighted Try-Once Discard Protocol 6

Design of Recursive Filtering Scheme via An Improved Weighte...

引用

6th International Conference on Industrial Artificial Intelligence, IAI 2024

作者： Zheng, Kaiwen Hu, Jun Du, Junhua Yu, Hui Harbin University of Science and Technology Department of Applied Mathematics Harbin150080 China Harbin University of Science and Technology Heilongjiang Prov. Key Lab. of Optimization Control and Intelligent Analysis for Complex Systems Harbin150080 China School of Automation Harbin University of Science and Technology Harbin150080 China

ISBN: (纸本)9798350356618

This paper investigates the recursive filtering (RF) problem for stochastic multi-rate (MR) systems, where the information transmission is regulated by an improved weighted try-once-discard protocol (IWTODP). In order to reduce communication overhead and mitigate network congestion, the IWTODP is firstly proposed and designed to schedule the order of data transmission from the sensors. The main objective of this paper is to design a new RF scheme to minimize the upper bound (UB) on the filtering error (FE) covariance in each iteration step in the presence of IWTODP and MR sampling. In particular, an iterative way is given to provide the expression form of the gain of RF. Finally, the effectiveness of the proposed RF method is illustrated through simulation example. © 2024 IEEE.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Structure deformation of Ni-Fe-Se enables efficient oxygen evolution via RE atoms doping

引用

Rare Metals 2025年第1期44卷 336-348页

作者： Hong-Rui Zhao Cheng-Zong Yuan Cong-Hui Li Wen-Kai Zhao Fu-Ling Wu Lei Xin Hong Yin Shu-Feng Ye Xiao-Meng Zhang Yun-Fa Chen Jiangxi Province Research Institute of Rare Earths Ganjiang Innovation AcademyChinese Academy of SciencesGanzhou341119China School of Rare Earths University of Science and Technology of ChinaHefei230026China Key Laboratory of Hunan Province for Advanced Carbon-Based Functional Materials School of Chemistry and Chemical EngineeringHunan Institute of Science and TechnologyYueyang414006China State Key Laboratory of Multiphase Complex Systems Institute of Process EngineeringChinese Academy of SciencesBeijing100190China

The development of cost-effective and highly stable electrocatalysts for oxygen evolution reactions holds paramount importance in practical hydrogen ***,we present a novel self-supported electrode comprising Ce-doped Ni-Fe-Se nanosheets grown on carbon cloth(Ni-Fe-Ce-Se/CC).This electrode was synthesized through a selenylation process,utilizing Ni-Fe-Ce-layered double hydroxide/carbon cloth(Ni-Fe-Ce LDH/CC)as the ***,Ni-Fe-Ce-Se/CC electrode demonstrates remarkable performance,requiring a low overpotential of 300 mV to attain a current density of 100 mA·cm^(-2)under harsh alkaline ***,the electrode exhibits exceptional stability during continuous operation for 100 *** into the underlying mechanisms was gained through a combination of experimental results and density functional theory *** findings reveal that Ce doping induces crystal structure deformation in Ni-Fe-Se and enhances electron enrichment around Ni *** structural modification optimizes the adsorption energy of oxygen-based intermediates on the Ni-Fe-Se *** work offers a valuable strategy for regulating the electron transfer and adsorption capabilities of transition metal selenide electrocatalysts through RE atoms doping,opening new avenues for enhanced electrocatalytic performance.

关键词： Ce doping Structure deformation Ni-Fe-Se Electron transfer Oxygen evolution

来源：评论

学校读者我要写书评

暂无评论

Distributed Optimization and Scaling Design for Solving Sylvester Equations

引用

Journal of systems science & complexity 2024年第6期37卷 2487-2510页

作者： CHENG Songsong YU Xin ZENG Xianlin LIANG Shu HONG Yiguang Anhui Engineering Laboratory of Human-Robot Integration System and Intelligent Equipment School of Electrical Engineering and AutomationAnhui UniversityHefei 230601China Key Laboratory of Intelligent Control and Decision of Complex Systems School of AutomationBeijing Institute of TechnologyBeijing 100081China Department of Control Science and Engineering Tongji UniversityShanghai 201804China Shanghai Research Institute for Intelligent Autonomous Systems Tongji UniversityShanghai 201210China

This paper develops distributed algorithms for solving Sylvester *** authors transform solving Sylvester equations into a distributed optimization problem,unifying all eight standard distributed matrix *** the authors propose a distributed algorithm to find the least squares solution and achieve an explicit linear convergence *** results are obtained by carefully choosing the step-size of the algorithm,which requires particular information of data and Laplacian *** avoid these centralized quantities,the authors further develop a distributed scaling technique by using local information *** a result,the proposed distributed algorithm along with the distributed scaling design yields a universal method for solving Sylvester equations over a multi-agent network with the constant step-size freely chosen from configurable ***,the authors provide three examples to illustrate the effectiveness of the proposed algorithms.

关键词： Distributed optimization least squares solution linear convergence rate step-size interval Sylvester equation

来源：评论

学校读者我要写书评

暂无评论

Interaction graph learning of line cascading failure in power networks and its statistical properties

引用

Energy Informatics 2023年第1期6卷 17页

作者： Ghasemi, Abdorasoul de Meer, Hermann Kantz, Holger Faculty of Computer Engineering K. N. Toosi University of Technology Tehran Iran Faculty of Computer Science and Mathematics Passau University Passau Germany Max Planck Institute for the Physics of Complex Systems Dresden Germany

We consider line failure cascading in power networks where an initial random failure of a few lines leads to consecutive other line overloads and failures before the system settles in a steady state. Such cascades are rooted in non-obvious, long-range, and higher-order couplings among the lines’ flows induced by physical constraints on the network. Failure interaction graph encodes which and to what extent other lines in a networked system are affected after each line failure and can help to predict the final state after an initial disturbance. We perform data analytics on the final lines’ steady states of cascade trajectories to infer a specific line’s state given the states of others. We use a generative model to reconstruct possible steady states, and a predictive model aims to predict the probability of each line’s failures after the initial failure as a regression problem. The generative model uses regularized pseudolikelihood estimator to infer interaction weights by solving the inverse Ising problem and deploys Glauber dynamics to generate steady states. The discriminative model uses boosted trees to efficiently learn over training and predict over test data the state of each line as a target finding an appropriate subset of other lines’ states as explanatory variables. We analyze the degree distribution of the corresponding interaction graphs to study the number of other components affected by each line failure (out-degree) or the number of lines that affect the state of a given line (in-degree). Both models show that the in-degree follows a power-law distribution. Finally, we discuss the possible application of the interaction graph for early link removal to mitigate the failure-cascading consequences. © 2023, The Author(s).

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

A Unified Information Diffusion Prediction Model Based on Multi-task Learning 9th

A Unified Information Diffusion Prediction Model Based on M...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Shang, Yingdan Zhou, Bin Zeng, Xiang Chen, Kai College of Computer Science and Technology National University of Defense Technology Changsha China Key Lab of Software Engineering for Complex Systems School of Computer National University of Defense Technology Changsha China

ISBN: (纸本)9783031466731

The prediction of online information diffusion trends on social networks is crucial for understanding people’s interests and concerns, and has many real-world applications in fields such as business, politics and social security. Existing research on information diffusion prediction has predominantly focused on either macro level prediction of the future popularity of online information or micro level user activation prediction. However, information diffusion prediction on micro or macro level only may lead to one-sided prediction results, and there is a lack of research on implementing micro and macro level diffusion prediction tasks at the same time. Since micro and macro level diffusion prediction tasks are related to each other, we propose a unified information diffusion model which can jointly predicting the micro level user activation probability and macro level information popularity based on multi-task learning framework. We utilize graph neural network to learn user representation from both the information cascades and social network structure. Comparing with micro and macro level baseline methods separately, the prediction results of our proposed model outperform all baseline methods and proves the effectiveness of the proposed method. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

AMCheX: Accurate Analysis of Missing-Check Bugs for Linux Kernel

引用

Journal of Computer science & technology 2021年第6期36卷 1325-1341页

作者： Ying-Jie Wang Liang-Ze Yin Wei Dong Key Laboratory of Software Engineering for Complex Systems College of Computer Science National University of Defense TechnologyChangsha 410073China

The Linux kernel adopts a large number of security checks to prevent security-sensitive operations from being executed under unsafe *** a security-sensitive operation is unchecked,a missing-check issue *** check is a class of severe bugs in software programs especially in operating system kernels,which may cause a variety of security issues,such as out-of-bound accesses,permission bypasses,and privilege *** to the lack of security specifications,how to automatically identify security-sensitive operations and their required security checks in the Linux kernel becomes a challenge for missing-check *** this paper,we present an accurate missing-check analysis method for Linux kernel,which can automatically infer possible security-sensitive ***,we first automatically identify all possible security check functions of *** according to their callsites,a two-direction analysis method is leveraged to identify possible security-sensitive operations.A missing-check bug is reported when the security-sensitive operation is not protected by its corresponding security *** have implemented our method as a tool,named AMCheX,on top of the LLVM(Low Level Virtual Machine)framework and evaluated it on the Linux *** reported 12 new missing-check bugs which can cause security *** of them have been confirmed by Linux maintainers.

关键词： security check function security-sensitive operation program analysis missing-check

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Discovery of Nonlinear Dynamical systems from Noisy and Sparse Observations

Data-Driven Discovery of Nonlinear Dynamical Systems from No...

引用

2024 International Conference on New Trends in Computational Intelligence, NTCI 2024

作者： Zhu, Wei Pei, Chao Liang, Yulan Chen, Zhang Li, Jingsui School of Science Chongqing University of Posts and Telecommunications Chongqing China Key Laboratory of Intelligent Analysis and Decision on Complex Systems Chongqing China College of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing China

ISBN: (纸本)9798331517021

Sparse Identification of Nonlinear Dynamics (SINDy) is a data-driven algorithm for interpretability mod-eling. SINDy has a strong ability to learn dynamical systems from time series data. Sparse Identification of Nonlinear Dynamics (SINDy) can extract equations from data, but its performance will degrade when data has noise or sparse. In order to deal with this case, the idea of Monte Carlo Markov Chain (MCMC) is introduced, which is used to optimally select models. The SINDy with MCMC (MCMC-SINDy) can comprehensively discover model structures by employing random samples in data space. Simulation results show that MCMC-SINDy is more robust than SINDy with 1 % -15 % levels of noise or sparse 0.5. These results are promising for the discovery of governing equations for complex systems in neuroscience, power grids, epidemiology, finance or ecology, where governing equations have remained elusive. mportantly, compared to existing machine learning methods, the accuracy of modeling using MCMC SINDy is higher. © 2024 IEEE.

关键词： Markov chains

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

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

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

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

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：