检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Wang, Xuhong Jiang, Haoyu Yu, Yi Yu, Jingru Lin, Yilun Yi, Ping Wang, Yingchun Yu, Qiao Li, Li Wang, Fei-Yue Shanghai Artificial Intelligence Laboratory Shanghai200433 China School of Cyber Science and Engineering Shanghai Jiao Tong University Shanghai200240 China Department of Automation BNRist Tsinghua University Beijing100084 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Large Language Models (LLMs) are increasingly integrated into diverse industries, posing substantial security risks due to unauthorized replication and misuse. To mitigate these concerns, robust identification mechanisms are widely acknowledged as an effective strategy. Identification systems for LLMs now rely heavily on watermarking technology to manage and protect intellectual property and ensure data security. However, previous studies have primarily concentrated on the basic principles of algorithms and lacked a comprehensive analysis of watermarking theory and practice from the perspective of intelligent identification. To bridge this gap, firstly, we explore how a robust identity recognition system can be effectively implemented and managed within LLMs by various participants using watermarking technology. Secondly, we propose a mathematical framework based on mutual information theory, which systematizes the identification process to achieve more precise and customized watermarking. Additionally, we present a comprehensive evaluation of performance metrics for LLM watermarking, reflecting participant preferences and advancing discussions on its identification applications. Lastly, we outline the existing challenges in current watermarking technologies and theoretical frameworks, and provide directional guidance to address these challenges. Our systematic classification and detailed exposition aim to enhance the comparison and evaluation of various methods, fostering further research and development toward a transparent, secure, and equitable LLM ecosystem. Copyright © 2024, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

The Shadow of Fraud: The Emerging Danger of AI-powered Social Engineering and its Possible Cure

arXiv

引用

arXiv 2024年

作者： Yu, Jingru Yu, Yi Wang, Xuhong Lin, Yilun Yang, Manzhi Qiao, Yu Wang, Fei-Yue Shanghai Artificial Intelligence Laboratory Shanghai200240 China The Macau Institute of Systems Engineering Macau University of Science and Technology China Eversec Technology Company Ltd. Beijing100080 China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

Social engineering (SE) attacks remain a significant threat to both individuals and organizations. The advancement of Artificial Intelligence (AI), including diffusion models and large language models (LLMs), has potentially intensified these threats by enabling more personalized and convincing attacks. This survey paper categorizes SE attack mechanisms, analyzes their evolution, and explores methods for measuring these threats. It highlights the challenges in raising awareness about the risks of AI-enhanced SE attacks and offers insights into developing proactive and adaptable defense strategies. Additionally, we introduce a categorization of the evolving nature of AI-powered social engineering attacks into"3E phases": Enlarging, wherein the magnitude of attacks expands through the leverage of digital media;Enriching, introducing novel attack vectors and techniques;and Emerging, signifying the advent of novel threats and methods. Moreover, we emphasize the necessity for a robust framework to assess the risk of AI-powered SE attacks. By identifying and addressing gaps in existing research, we aim to guide future studies and encourage the development of more effective defenses against the growing threat of AI-powered social engineering. Copyright © 2024, The Authors. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

AdvDiffuser: Generating Adversarial Safety-Critical Driving Scenarios via Guided Diffusion

AdvDiffuser: Generating Adversarial Safety-Critical Driving ...

引用

IEEE/RSJ International Conference on Intelligent Robots and systems (IROS)

作者： Yuting Xie Xianda Guo Cong Wang Kunhua Liu Long Chen School of Computer Science and Engineering Sun Yat-Sen University School of Computer Science Wuhan University State Key Laboratory for Management and Control of Complex Systems at the Institute of Automation Chinese Academy of Sciences School of Mechanical and Automotive Engineering Qingdao University of Technology

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Safety-critical scenarios are infrequent in natural driving environments but hold significant importance for the training and testing of autonomous driving systems. The prevailing approach involves generating safety-critical scenarios automatically in simulation by introducing adversarial adjustments to natural environments. These adjustments are often tailored to specific tested systems, thereby disregarding their transferability across different systems. In this paper, we propose AdvDiffuser, an adversarial framework for generating safety-critical driving scenarios through guided diffusion. By incorporating a diffusion model to capture plausible collective behaviors of background vehicles and a lightweight guide model to effectively handle adversarial scenarios, AdvDiffuser facilitates transferability. Experimental results on the nuScenes dataset demonstrate that AdvDiffuser, trained on offline driving logs, can be applied to various tested systems with minimal warm-up episode data and outperform other existing methods in terms of realism, diversity, and adversarial performance.

关键词： Training Diffusion models Intelligent robots Autonomous vehicles Testing

来源：评论

学校读者我要写书评

暂无评论

Valuing Equity-Linked Guaranteed Minimum Death Benefits with European-Style Asian Payoffs Under the Regime-Switching Diffusion Process with Jump

SSRN

引用

SSRN 2022年

作者： Wang, Yayun Liu, Shengda Key Laboratory of Intelligent Analysis and Decision on Complex Systems Chongqing University of Posts and Telecommunications Chongqing400065 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing100190 China

In this paper, we consider a novel and efficient method to price equity-linked guaranteed minimumdeath benefits (GMDB) with European-style geometric Asian and arithmetic Asian payoffs. In thesituation of continuous transition of market economy, we assume that the underlying asset price processfollows regime-switching Ĺevy model and use complex Fourier series (CFS) expansion method to derivethe approximate value of GMDB products. The error analysis shows an exponential convergence rateunder geometric Asian and arithmetic Asian payoffs. Furthermore, the CFS approach is comparedwith other Fourier transform methods and Monte Carlo simulation, the numerical experiment resultsillustrate our method has a distinct advantage over other methods in both efficiency and accuracy. © 2022, The Authors. All rights reserved.

关键词： Monte Carlo methods

来源：评论

学校读者我要写书评

暂无评论

Stealthy False Data Injection Attacks against Extended Kalman Filter Detection in Power Grids

Stealthy False Data Injection Attacks against Extended Kalma...

引用

2021 International Conference on Information, Cybernetics, and Computational Social systems, ICCSS 2021

作者： Liu, Yifa Xue, Wenchao He, Shuping Cheng, Long Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Institute of Automation Beijing100190 China Chinese Academy of Sciences Key Laboratory of System and Control Academy of Mathematics and System Science Beijing100190 China Anhui University School of Electrical Engineering and Automation Hefei230601 China

ISBN: (纸本)9781665402453

The power grid is a kind of national critical infrastructure directly affiliated to human daily life. Because of the vital functions and potentially significant losses, the power grid becomes an excellent target for many malicious attacks. Due to the special nonlinear measurements, many detection methods do not match the grid very well. The extended Kalman filter based detection is one of the few methods suitable for nonlinear system detection, and therefore can be used in power system to spot malicious attacks. However, the reliability and effectiveness of the extended Kalman filter based detection have not been fully studied and adequately guaranteed. By proposing a two-step false data injection attack strategy, this paper gives a stealthy way to inject false data of increasing magnitude into the power grid, which can eventually cause a certain degree of deviation of the grid state without being detected. In the simulation, the method proposed in this paper caused a voltage deviation of more than 25% before being discovered in the power system. © 2021 IEEE.

关键词： Extended Kalman filters

来源：评论

学校读者我要写书评

暂无评论

Signal Detection Method Based on Social Relationship Strength in Vehicular Ad-hoc Networks ⁎

引用

IFAC-PapersOnLine 2024年第10期58卷 176-181页

作者： Yi Li Shuangshuang Han Yongqiang Bai Fei-Yue Wang School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China and Key Laboratory of Ocean Observation Technology MNR Tianjin China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing China and Beijing Huairou Academy of Parallel Sensing Beijing China The State Key Laboratory for Management and Control of Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

In the case of scarce communication resources, the importance of different vehicle communication levels is self-evident. They not only affect the efficiency of information exchange between vehicles and driving safety, but also directly affect the rational allocation and utilization of communication resources. Therefore, this paper proposes a signal detection method based on vehicle social relationship strength (SRS) in vehicular ad-hoc networks (VANETs) scenario, and integrates the SRS information into the data to be transmitted. In this method, minimum mean square error (MMSE) signal detection algorithm is selected for simulation, and Rayleigh channel and Rician channel are selected for simulation scenarios. This method makes full use of the intensity of social relationship between vehicles, and realizes the efficient transmission of data and the accurate transmission of communication level. Experimental verification shows that the method performs well in the VANETs scenario, and provides a new communication method for intelligent transportation, social network and other applications, which is expected to promote the technical progress and application development in related fields.

关键词： VANETs Social relation strength Image data transmission MMSE detection Intelligent transportation Social networking

来源：评论

学校读者我要写书评

暂无评论

ReCUS: Reconvolution and Upsampling Network for Object Detection 7

ReCUS: Reconvolution and Upsampling Network for Object Detec...

引用

7th IEEE International Conference on Cloud Computing and Intelligence systems, CCIS 2021

作者： Li, Fudong Gao, Dongyang Yang, Yuequan Cao, Zhiqiang Wang, Wei Yangzhou225000 China Institute of Automation Chinese Academy of Sciences State Key Laboratory of Management and Control for Complex Systems Beijing100190 China Affiliated Hospital of Yangzhou University Yangzhou225012 China

ISBN: (纸本)9781665441490

Most of the mainstream object detection models such as RetinaNet, SSD, YOLO, and Faster RCNN hardly achieve a good balance between detection accuracy and speed. A major reason is rich deep feature semantic information of images is not fully exploited. To solve this problem, a novel deep convolutional network structure termed as reconvolution and upsampling network (ReCUS) is proposed. In the ReCUS, a modified path aggregation network(mPAN) is added after the backbone, which is beneficial to strengthen the foreground salient feature information and weaken background information. Moreover, two new spatial pyramid pooling (SPP) modules are embedded before output heads for multi-scale fusion of local and global features. The experiments show that the effectiveness of our proposed ReCUS. Furthermore, the better detectability of the ReCUS network is demonstrated for both small scale objects and large scale objects. © 2021 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Path Following and Collision Avoidance of a Ribbon-Fin Propelled Underwater Biomimetic Vehicle-Manipulator System

SSRN

引用

SSRN 2022年

作者： He, Yanbing Dong, Xiang Wang, Yu Wang, Shuo Cheng, Long School of Electrical Engineering and Automation Anhui University Hefei230601 China State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences China

This paper addresses the problem of path following and dynamic obstacle avoidance for underwater biomimetic vehicle-manipulator system (UBVMS). Firstly, the general kinematics and dynamics models of underwater vehicles are presented;then a nonlinear model predictive control (NMPC) scheme is employed to track a reference path and collision avoidance simultaneously. Moreover, to minimize the tracking error and a higher degree of robustness, improved extended state observers are used to estimate model uncertainties and disturbances to be fed into the NMPC prediction model. On top of this, the proposed method also considers the uncertainty of the state estimator, while combining a priori estimation of the Kalman filter to reasonably predict the position of dynamic obstacles during short periods. Finally, simulations and experimental results are carried out to assess the validity of the proposed method in case of disturbances and constraints. © 2022, The Authors. All rights reserved.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

An intelligent maritime scene frame prediction based on digital twins technology 1

An intelligent maritime scene frame prediction based on digi...

引用

1st IEEE International Conference on Digital Twins and Parallel Intelligence, DTPI 2021

作者： Guo, Zhong-Zheng Wang, Kai Qin, Jiang-Yi Li, Xian-Bin Ran, De-Chao Shen, Yu Unmanned Systems Research Center National Innovation Institute of Defense Technology Academy of Military Science Beijing China Institute of Automation Chinese Academy of Sciences The State Key Laboratory for Management and Control of Complex Systems Beijing China

ISBN: (纸本)9781665433372

This paper proposes a scene frame prediction system based on digital twin technology. The system is mainly composed of an unmanned perception module, a communication link module, a command center module that provides intelligent computing services, and an interaction and visualization module for human operators. These modules together constitute a system for predicting and recovery the time-series matrix composed of scene frames and object frames. At the same time, in view of the current problems of lack of real-time information and long response time in the maritime search and rescue (SAR) field, this paper instantiates the above system to improve the existing SAR system. Satellites and unmanned vehicles perceive part of the scene data of the real cyber-physical system in real-time and divide them into multiple frames according to the timestamps. In addition, this paper also proposes an environmental graph-attention network (Env-GAT) to achieve efficient and reliable frame predicting. Finally, this paper verifies that the performance of the spatiotemporal attention graph network model has reached the optimal level through computational experiments. © 2021 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

PiAGI: The Concept, Mechanism and Framework

PiAGI: The Concept, Mechanism and Framework

引用

Digital Twins and Parallel Intelligence (DTPI), IEEE International Conference on

作者： Qiang Li Zhuoya Ju Lili Fan Xin Liu Wenhua Liu Feiyue Wang Scientific and Technological Innovation Center Beijing China The School of Automation Beijing Institute of Technology Beijing China School of Big Data & Cyber Security China University of Petroleum Qingdao China The State Key Laboratory of Management and Control for Complex Systems Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350349252

ISBN: (纸本)9798350349269

As social production and living spaces gradually expand from the physical and information domains to the cognitive and social domains, this article addresses the new changes brought about by these expansions. Starting from the new impact of era of intelligent connectivity on social cognitive management, it analyzes the urgent need to enhance social cognitive management capabilities centered on cognitive decision-making, identifying the core key as Adversarial Generated Intelligence (AGI). It delves into the conceptual characteristics, operating mechanisms, and winning strategies of AGI, identifies the new challenges it faces, and proposes a Parallel Intelligence empowering AGI (PiAGI) system architecture through the empowerment of parallel intelligence. This provides theoretical support for improving social cognitive management capabilities centered on cognitive decision-making.

关键词： Decision making systems architecture Production Digital twins Faces

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：