检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Zhu, Zijian Zhang, Yichi Chen, Hai Dong, Yinpeng Zhao, Shu Ding, Wenbo Zhong, Jiachen Zheng, Shibao Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Dept. of Comp. Sci. and Tech. Institute for AI THBI Lab BNRist Center Tsinghua University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Anhui University Information Materials and Intelligent Sensing Laboratory of Anhui Province China SAIC Motor AI Lab China Zhongguancun Laboratory China

3D object detection is an essential perception task in autonomous driving to understand the environments. The Bird’s-Eye-View (BEV) representations have significantly improved the performance of 3D detectors with camera inputs on popular benchmarks. However, there still lacks a systematic understanding of the robustness of these vision-dependent BEV models, which is closely related to the safety of autonomous driving systems. In this paper, we evaluate the natural and adversarial robustness of various representative models under extensive settings, to fully understand their behaviors influenced by explicit BEV features compared with those without BEV. In addition to the classic settings, we propose a 3D consistent patch attack by applying adversarial patches in the 3D space to guarantee the spatiotemporal consistency, which is more realistic for the scenario of autonomous driving. With substantial experiments, we draw several findings: 1) BEV models tend to be more stable than previous methods under different natural conditions and common corruptions due to the expressive spatial representations;2) BEV models are more vulnerable to adversarial noises, mainly caused by the redundant BEV features;3) Camera-LiDAR fusion models have superior performance under different settings with multi-modal inputs, but BEV fusion model is still vulnerable to adversarial noises of both point cloud and image. These findings alert the safety issue in the applications of BEV detectors and could facilitate the development of more robust models. Code available at https: //***/zzj403/BEV_Robust. Copyright © 2023, The Authors. All rights reserved.

关键词： Birds

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based Distributed Storage System for Task Offloading in Vehicular Edge computing

Blockchain-based Distributed Storage System for Task Offload...

引用

IEEE International Conference on Big Data and Cloud computing (BdCloud)

作者： Yutian Zhang Bing Tang Qing Yang Xiaoyuan Zhang Jincheng Luo Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China School of Information and Communication Engineering Guangzhou Maritime University Guangzhou China

With the deepening requirements of development for the Internet of Vehicles technology, intelligent vehicles need to complete the complex task in a fast response time to meet the needs, which brings great challenges to reliable vehicle service provision. In order to solve this problem, we propose a task offloading scheme into the Internet of Vehicles, which can reduce the execution time of tasks. In this paper, we introduce a location-aware distributed storage system called LDSS to support task offloading. Data can be written, stored, computed and read out through different mobile edge servers. Firstly, the identity of the vehicle is stored on the blockchain, and then the vehicle needs to offload the data to the nearest mobile edge server. Then, the storage node and computing node are selected based on the time optimization strategy. Finally, by predicting the location of the vehicle, the mobile edge server nearest to the predicted vehicle location is selected as the access node for result downloading. After validating the identity of vehicle based on blockchain technology, the output result is returned to the vehicle. The experiments show that our proposed task offloading scheme based on blockchain can effectively achieve the effect of low latency and faster task response, as well as ensure data security.

关键词： Blockchains Servers Reliability Time factors Task analysis Low latency communication Optimization

来源：评论

学校读者我要写书评

暂无评论

A Dual-Polarized Antenna For 5G N78 Application

A Dual-Polarized Antenna For 5G N78 Application

引用

IEEE Asia-Pacific Conference on Antennas and Propagation (APCAP)

作者： Jiakang Pan Junwei Qi Yingsong Li College of Information and Communication Engineering Harbin Engineering University China College of Computer Science and Technology Harbin Engineering University China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei China

A compact dual polarization dipole antenna for the application to 5G base station is investigated, which is composed of radiator, baluns, and metal reflector, having an impendence bandwidth of 23.6% with VSWR<1.5. The dual-polarized antenna has a high ports isolation, high cross-polarization and high gain in operating bandwidth. The results indicate that this work can operate in entire N78 band and provide potential application for 5G base station.

关键词： Base stations 5G mobile communication Dipole antennas Baluns Metals Bandwidth Reflector antennas

来源：评论

学校读者我要写书评

暂无评论

Squared Sine Adaptive Algorithm and Its Performance Analysis

TechRxiv

引用

TechRxiv 2023年

作者： Li, Yingsong Huang, Xinqi Zakharov, Yuriy Miao, Yongchun Huang, Zhixiang Li, Liping The College of Information and Communication Engineering Harbin Engineering University Harbin150001 China The Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University Hefei230601 China The School of Physics Engineering and Technology University of York YorkYO10 5DD United Kingdom

We presents a squared sine functioned adaptive (SSA) algorithm for acoustic-echo-cancellation (AEC) applications in-presence-of impulsive noise. In the development of the SSA algorithm, a novel cost function is constructed by exerting a sliding window type squared sine function on the estimation error vector, which provides robustness in the impulsive-noise environments and speed-ups convergence when the input is colored signals. Theoretical models for predicting the mean-weight-behavior, transient excess-mean-square-error (EMSE) behavior, and tracking behavior are presented. Moreover, the optimal step size and minimum EMSE of the tracking performance are provided. The computation complexity of SSA algorithm has also been investigated. Numerical experiments demonstrate that the theoretical results match well with simulation results and show the superiority of the proposed SSA algorithm against known algorithms in AEC applications. © 2023, CC BY.

关键词： Adaptive filters

来源：评论

学校读者我要写书评

暂无评论

An Authentication Mechanism for IoT Devices Based on Traceable and Revocable Identity-Based Encryption 7th

An Authentication Mechanism for IoT Devices Based on Tra...

引用

7th International Conference on Artificial Intelligence and Security, ICAIS 2021

作者： Xia, Fei Mao, Jiaming Shao, Zhipeng Xu, Liangjie Zhao, Ran Yang, Yunzhi State Grid Jiangsu Electric Power Co Ltd. Information and Telecommunication Branch Nanjing210024 China Institute of Information and Communication State Grid Key Laboratory of Information and Network Security Global Energy Interconnection Research Institute Nanjing Jiangsu210003 China Anhui Jiyuan Software Co. Ltd SGITG Hefei Anhui230088 China

ISBN: (纸本)9783030786113

To solve low computing efficiency and high computational energy consumption in the traditional Public-key Infrastructure cryptosystem in the authentication of IoT devices, an authentication scheme for IoT devices based on the Identity-based Encryption is proposed in this paper, which is realized by introducing traceable and revocable mechanisms. The effective management of the secret key of the suspicious devices by the authentication center and the reasonable accountability of the dishonest private key generator (PKG) are realized. Finally, through the security proof, it is verified that the Identity-based Encryption designed in this paper can meet the security of the Chosen Ciphertext Attack (CCA), indicating that the scheme has high practicability and security. © 2021, Springer Nature Switzerland AG.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

A Proposed Radio Environment Monitoring System of Ali Observatory 35

A Proposed Radio Environment Monitoring System of Ali Observ...

引用

35th General Assembly and Scientific Symposium of the International Union of Radio Science, URSI GASS 2023

作者： Zhang, Haiyan Wang, Yu Huang, Shijie Hu, Hao Zhao, Chuanjiang Wu, Guifang National Astronomical Observatories Chinese Academy of Sciences 20A Datun Road Chaoyang District Beijing100101 China Hebei Key Laboratory of Radio Astronomy Technology Hebei Shijiazhuang050081 China Research Center for Intelligent Computing Platforms Zhejiang Laboratory Zhongtai Street Yuhang District Zhejiang Hangzhou311100 China Beijing Boer Communication Technology Co. Ltd Zhongguancun Software Park No. 8 Dongbei Wangxi Road Haidian District Beijing100089 China China Electric Power Research Institute Co. Ltd 15 Qinghe Xiaoying East Road Haidian District Beijing100192 China

ISBN: (纸本)9789463968096

With its extremely dry air and high altitude above 5000 meters, the Ail Observatory located in the Tibet plateau has been a promising site for several astronomical instruments working in the optical or millimeter wave bands. In addition to protect the dark sky around the Ali Observatory, the measures to protect local radio environment have also been discussed. Based on the requirements of radio astronomical instruments, a radio environment monitoring system has been proposed. This paper describes the preliminary design of the system, including the technical specification and the system composition. In the near future, this system will be put into use. © 2023 International Union of Radio Science.

关键词： Observatories

来源：评论

学校读者我要写书评

暂无评论

No-Reference Image Quality Assessment Based on Active Reasoning Module

No-Reference Image Quality Assessment Based on Active Reason...

引用

IEEE International Conference on Electronic Information and communication Technology (ICEICT)

作者： Junwei Qi Yuhao Deng Qingchun Wang Zhen Yang Yingsong Li College of Information and Communication Engineering Harbin Engineering University Harbin China College of Computer Science and Technology Harbin Engineering University Harbin China Shanghai Yanding Information Technology Co. Ltd. Shanghai China Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education Anhui University China

We present a no-reference image-quality - assessment algorithm based on active reasoning module. This algorithm has three modules: the feature extraction module, the active reasoning module, and the quality assessment module. The active reasoning module incorporates the generator component of the generative adversarial network and enhances its structure with the Res2Net architecture. By integrating this module into the backbone feature extraction network, we improve the receptive field of each convolutional layer, enabling the network to capture information at different scales of the image. To preserve the texture information of the image, we input the gradient map of the distorted image, the distorted image itself, and the image features generated by the generator into the quality assessment module, which has a multi-feature regression networks. This module establishes a mapping model from image-feature to image-quality scores. We conducted experimental analysis of this algorithm on three widely used public datasets, confirming the excellent performance and superiorities of the presented algorithm. The results validate the effectiveness of the designed algorithm and its ability to assess image quality accurately.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

Securely Fine-tuning Pre-trained Encoders Against Adversaria...

引用

IEEE Symposium on Security and Privacy

作者： Ziqi Zhou Minghui Li Wei Liu Shengshan Hu Yechao Zhang Wei Wan Lulu Xue Leo Yu Zhang Dezhong Yao 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 Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology Hubei Engineering Research Center on Big Data Security Hubei Key Laboratory of Distributed System Security School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (数字)9798350331301

ISBN: (纸本)9798350331318

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the *** this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six d

关键词： Training Adaptation models Sensitivity Accuracy Self-supervised learning Genetics Feature extraction

来源：评论

学校读者我要写书评

暂无评论

MISA: Unveiling the Vulnerabilities in Split Federated Learning

MISA: Unveiling the Vulnerabilities in Split Federated Learn...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wei Wan Yuxuan Ning Shengshan Hu Lulu Xue Minghui Li Leo Yu Zhang Hai Jin School of Cyber Science and Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Computer Science and Technology Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University Cluster and Grid Computing Lab

Federated learning (FL) and split learning (SL) are prevailing distributed paradigms in recent years. They both enable shared global model training while keeping data localized on users’ devices. The former excels in parallel execution capabilities, while the latter enjoys low dependence on edge computing resources and strong privacy protection. Split federated learning (SFL) combines the strengths of both FL and SL, making it one of the most popular distributed architectures. Furthermore, a recent study has claimed that SFL exhibits robustness against poisoning attacks, with a fivefold improvement compared to FL in terms of *** this paper, we present a novel poisoning attack known as $\color{Fuchsia} {{\text{MISA}}}$. It poisons both the top and bottom models, causing a misalignment in the global model, ultimately leading to a drastic accuracy collapse. This attack unveils the vulnerabilities in SFL, challenging the conventional belief that SFL is robust against poisoning attacks. Extensive experiments demonstrate that our proposed MISA poses a significant threat to the availability of SFL, underscoring the imperative for academia and industry to accord this matter due attention.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DarkSAM: Fooling Segment Anything Model to Segment Nothing

arXiv

引用

arXiv 2024年

作者： Zhou, Ziqi Song, Yufei Li, Minghui Hu, Shengshan Wang, Xianlong Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab China Cluster and Grid Computing Lab China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Frequency domain analysis

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：