检索结果-内蒙古大学图书馆

Team: An taylor expansion-based method for generating adversarial examples

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Qian, Ya-guan Zhang, Xi-Ming Swaileh, Wassim Wei, Li Wang, Bin Chen, Jian-Hai Zhou, Wu-Jie Lei, Jing-Sheng School of Big-Data Science Zhejiang University of Science and Technology Hangzhou310023 China Network and Information Security Laboratory of Hangzhou Hikvision Digital Technology Co. Ltd. Hang Zhou310052 China College of Computer Science and Technology Zhejiang University Hangzhou310058 China School of Information and Electronic Engineering Zhejiang University of Science and Technology Hangzhou310023 China Laboratoire ETIS UMR-CNRS 8051 CY Cergy Paris Université France

Although Deep Neural networks(DNNs) have achieved successful applications in many fields, they are vulnerable to adversarial *** training is one of the most effective methods to improve the robustness of DNNs, and it is generally considered as solving a saddle point problem that minimizes risk and maximizes ***, powerful adversarial examples can effectively replicate the situation of perturbation maximization to solve the saddle point *** method proposed in this paper approximates the output of DNNs in the input neighborhood by using the Taylor expansion, and then optimizes it by using the Lagrange multiplier method to generate adversarial examples. If it is used for adversarial training, the DNNs can be effectively regularized and the defects of the model can be improved. Copyright © 2020, The Authors. All rights reserved.

关键词： Deep neural networks

A Survey on Service Route and Time Prediction in Instant Delivery: Taxonomy, Progress, and Prospects

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wen, Haomin Lin, Youfang Wu, Lixia Mao, Xiaowei Cai, Tianyue Hou, Yunfeng Guo, Shengnan Liang, Yuxuan Jin, Guangyin Zhao, Yiji Zimmermann, Roger Ye, Jieping Wan, Huaiyu The Beijing Key Laboratory of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The Key Laboratory of Intelligent Passenger Service of Civil Aviation CAAC Beijing101318 China The School of Computing National University of Singapore Singapore College of Systems Engineering National University of Defense Technology Changsha China The School of Information Science and Engineering Yunnan University Kunming650091 China The Cainiao Network Hangzhou China The Alibaba Group Hangzhou China INTR Thrust and DSA Thrust The Hong Kong University of Science and Technology Guangzhou China

Instant delivery services, such as food delivery and package delivery, have achieved explosive growth in recent years by providing customers with daily-life convenience. An emerging research area within these services is service Route&Time Prediction (RTP), which aims to estimate the future service route as well as the arrival time of a given worker. As one of the most crucial tasks in those service platforms, RTP stands central to enhancing user satisfaction and trimming operational expenditures on these platforms. Despite a plethora of algorithms developed to date, there is no systematic, comprehensive survey to guide researchers in this domain. To fill this gap, our work presents the first comprehensive survey that methodically categorizes recent advances in service route and time prediction. We start by defining the RTP challenge and then delve into the metrics that are often employed. Following that, we scrutinize the existing RTP methodologies, presenting a novel taxonomy of them. We categorize these methods based on three criteria: (i) type of task, subdivided into only-route prediction, only-time prediction, and joint route&time prediction;(ii) model architecture, which encompasses sequence-based and graph-based models;and (iii) learning paradigm, including Supervised Learning (SL) and Deep Reinforcement Learning (DRL). Conclusively, we highlight the limitations of current research and suggest prospective avenues. We believe that the taxonomy, progress, and prospects introduced in this paper can significantly promote the development of this field. © 2023, CC BY.

关键词： Taxonomies

Beyond 10logm Array Gain: A Beamforming Method Under Non-Gaussian Noise and Multi-Sources

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Su, Xiruo Tao, Liurong Ren, Haoran Wu, Bin Ye, Lingyun College of Biomedical Engineering & Instrument Science Zhejiang University Hangzhou310027 China Key Laboratory of Geoscience Big Data and Deep Resource of Zhejiang Province School of Earth Sciences Zhejiang University Hangzhou310058 China Zhejiang Provincial Key Laboratory for Network Multimedia Technology Hangzhou310027 China Hainan Institute Zhejiang University Sanya572025 China Explosion and Seismic Sensing Research Center Advanced Technology Institute Zhejiang University Hangzhou310027 China

Researchers have applied deep learning techniques in the direction of arrival domain in various real-world applications, such as traffic positioning and hydro-acoustic detection. However, the effectiveness of these algorithms is dependent on the similarity of training data with actual data, which is challenging to obtain, particularly in hydro-acoustic environments. This is due to the limited array gain (AG) and constantly changing ambient noise. Moreover, the presence of non-Gaussian noise in the background further complicates the identification process, especially lower the basic 10logM AG. Additionally, the majority of existing algorithms are only capable of detecting up to four sources. To tackle this issue, we propose a novel method that employs a diagonal beam spectrum (DBS) feature to suppress non-Gaussian noise and enhance array gain. By utilizing DBS, our method surpasses the theoretical 10logM array gain and achieves an impressive 25logM array gain, while effectively detecting signals as low as -38dB (M denotes the number of sensors).We also use SA-U-NET, an image edge detection network based on DBS, to detect unlimited sound sources and optimize angular positioning. Our proposed method achieves up to 95.67% correctness (4 times better than the best baseline) in experiments , demonstrating the potential of DBS and SA-U-NET. © 2023, The Authors. All rights reserved.

关键词： Beamforming

Deep Learning Strategies for Addressing Anomalous Exposure in Image Processing: The FARDBUNet Approach 5

学校读者我要写书评

暂无评论

Deep Learning Strategies for Addressing Anomalous Exposure i...

5th International Conference on High Performance Big data and Intelligent Systems, HDIS 2023

作者： Zhou, Qi Yang, Kai Ke, Zunwang Wang, Gang Zhang, Yugui Jia, Yizhen Cao, Fengcai Ma, Junxiao Liu, Changlin Zhang, Kaijie Wu, Min School of Semiconductor Science and Technology South China Normal University GuangZhou510631 China CGNPC Uranium Industry Development Co. Ltd. Beijing100020 China School of Software Xinjiang University Urumqi830046 China School of Computing and Data Engineering NingboTech University Ningbo315100 China AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China School of Integrated Circuits University of Chinese Academy of Sciences Beijing100049 China Co. Ltd Beijing100176 China School of Information Beijing Forestry University Beijing100083 China

ISBN: (纸本)9798350394160

In real-world scenarios, capturing scenes with excessive dynamic range often leads to the partial loss of highlight or dark area information due to irradiance variations and limitations in the capture capabilities of imaging devices caused by their size and material constraints. This phenomenon gives rise to anomalous exposure problems and triggers the loss of crucial initial details, thereby becoming a significant obstacle to achieving high image quality. Despite numerous researchers’ integration of exposure compensation techniques into the imaging process, the anomalous exposure problem remains unsolved, hindering progress in image processing. Consequently, considerable research is valuable in implementing exposure calibration techniques on visual perception and multimedia devices. This dissertation proposes FARDBUNet, a novel end-to-end exposure calibration model designed to address the anomalous exposure problem. A key innovation of FARDBUNet is the incorporation of a fused attention mechanism, enabling the model to prioritize regions needing enhanced correction while accounting for the global exposure characteristics of the image. Additionally, to tackle the challenge of inadequate information availability in the localized areas due to exposure issues, we introduce an atrous residual dense block that efficiently captures local information by expanding the receptive field. Comprehensive tests validate the effectiveness of our suggested model, which performs on par with leading techniques on expansive exposure datasets. ©2023 IEEE.

关键词： Image enhancement

Larger receptive Field and Context Information for Pose estimation:Larger Gaussian kernel 5

学校读者我要写书评

暂无评论

Larger receptive Field and Context Information for Pose esti...

5th International Conference on High Performance Big data and Intelligent Systems, HDIS 2023

作者： Ma, Junxiao Yang, Kai Ke, Zunwang Wang, Gang Zhang, Yugui Cao, Fengcai Zhou, Qi Fei, Yang School of Information Beijing Forestry University Beijing100083 China CGNPC Uranium Industry Development Co. Ltd. Beijing100020 China School of Software Xinjiang University Urumqi830046 China School of Computing and Data Engineering NingboTech University Ningbo315100 China AnnLab Institute of Semiconductors Chinese Academy of Sciences Beijing100083 China Beijing Key Laboratory of Semiconductor Neural Network Intelligent Sensing and Computing Technology Beijing100083 China School of Integrated Circuits University of Chinese Academy of Sciences Beijing100049 China Co. Ltd Beijing100176 China School of Semiconductor Science and Technology South China Normal University GuangZhou510631 China

ISBN: (纸本)9798350394160

The field of pose estimation has a wide range of application prospects in various industries in the current era. With the continuous development of deep learning techniques, the effects in the field of human pose estimation are constantly being optimized. However, due to the influence of factors such as occlusion and human posture variability, it is easy to lead to inaccurate identification of keypoints and even keypoints’ missing and matching errors, there is still a lot of optimization space for the effect of pose estimation. In this paper, we propose an improvement to generate heatmaps in the training process: increase the radius of the Gaussian kernel and adjust the smoothness of Gaussian distribution to get a larger receptive field, encourage the model to use more context information in prediction, and control other parameters unchanged on the premise of using heatmap regression. Improve keypoint detection performance by optimizing this item. In the experiment, for the COCO-Keypoint data set, we selected different methods published in recent years, and after our improvement, we obtained better accuracy and performance than the original method, which proves the validity of our method. ©2023 IEEE.

关键词： Gaussian distribution

Disentangled Representation Learning with Transmitted Information Bottleneck

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Dang, Zhuohang Luo, Minnan Jia, Chengyou Dai, Guang Wang, Jihong Chang, Xiaojun Wang, Jingdong The School of Computer Science and Technology The Ministry of Education Key Laboratory of Intelligent Networks and Network Security The Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Shaanxi Xi’an710049 China The SGIT AI Laboratory Xi’an710048 China The State Grid Shaanxi Electric Power Company Ltd. State Grid Corporation of China Xi’an710048 China The School of Information Science and Technology University of Science and Technology of China Hefei230026 China Abu Dhabi United Arab Emirates Baidu Inc Beijing100085 China

Encoding only the task-related information from the raw data, i.e., disentangled representation learning, can greatly contribute to the robustness and generalizability of models. Although significant advances have been made by regularizing the information in representations with information theory, two major challenges remain: 1) the representation compression inevitably leads to performance drop;2) the disentanglement constraints on representations are in complicated optimization. To these issues, we introduce Bayesian networks with transmitted information to formulate the interaction among input and representations during disentanglement. Building upon this framework, we propose DisTIB (Transmitted Information Bottleneck for Disentangled representation learning), a novel objective that navigates the balance between information compression and preservation. We employ variational inference to derive a tractable estimation for DisTIB. This estimation can be simply optimized via standard gradient descent with a reparameterization trick. Moreover, we theoretically prove that DisTIB can achieve optimal disentanglement, underscoring its superior efficacy. To solidify our claims, we conduct extensive experiments on various downstream tasks to demonstrate the appealing efficacy of DisTIB and validate our theoretical analyses. Copyright © 2023, The Authors. All rights reserved.

关键词： Information theory

Trust and Risk Based on Access Control Model in Social Internet of Things

学校读者我要写书评

暂无评论

International Journal of network Security 2023年第5期25卷 736-744页

作者： Zhang, Hongbin Liu, Jian Zhao, Dongmei Liu, Bin Wang, Yanmei Fan, Fan School of Information Science and Engineering Hebei University of Science and Technology Shijiazhuang050000 China Hebei Key Laboratory of Network and Information Security Hebei Normal University Shijiazhuang050024 China School of Economics and Management Hebei University of Science and Technology Shijiazhuang050000 China Research Center of Big Data and Social Computing Hebei University of Scienc and Technology Shijiazhuang050000 China Hebei Geological Worker’s University Shijiazhuang050000 China

Integrating social networks and the Internet of Things has formed an emerging field of Social Internet of Things (IoT). Aiming to address the shortcomings of traditional TBAC (Trust based on Access Control) and ABAC (Attribute based on Access Control) in dynamic authorization and security, this paper proposes a hybrid access control model based on trust and risk for SIoT. The model supports social relationship-based trust assessment and risk prediction between SIoT nodes and integrates trust and risk values into SIoT security values through reasonable weight allocation. Furthermore, by simulating the safety requirements of different scenarios, it was verified that the model was efficient and more secure than the current models. © (2023). All Rights Reserved.

关键词： Authorization

Integrated Sensing and Communication Signals Toward 5G-A and 6G: A Survey

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wei, Zhiqing Qu, Hanyang Wang, Yuan Yuan, Xin Wu, Huici Du, Ying Han, Kaifeng Zhang, Ning Feng, Zhiyong The Key Laboratory of Universal Wireless Communications Ministry of Education School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing100876 China The National Engineering Lab for Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing100876 China Peng Cheng Laboratory Shenzhen518066 China Data61 CSIRO Sydney Australia The Department of Electrical and Computer Engineering University of Windsor WindsorONN9B 3P4 Canada The University of Science and Technology of China China Academy of Information and Communications Technology Beijing100191 China China Academy of Information and Communications Technology Beijing100191 China

Integrated sensing and communication (ISAC) has the advantages of efficient spectrum utilization and low hardware cost. It is promising to be implemented in the fifth-generation-advanced (5G-A) and sixth-generation (6G) mobile communication systems, having the potential to be applied in intelligent applications requiring both communication and high-accurate sensing capabilities. As the fundamental technology of ISAC, ISAC signal directly impacts the performance of sensing and communication. This article systematically reviews the literature on ISAC signals from the perspective of mobile communication systems, including ISAC signal design, ISAC signal processing and ISAC signal optimization. We first review the ISAC signal design based on 5G, 5G-A and 6G mobile communication systems. Then, radar signal processing methods are reviewed for ISAC signals, mainly including the channel information matrix method, spectrum lines estimator method and super resolution method. In terms of signal optimization, we summarize peak-to-average power ratio (PAPR) optimization, interference management, and adaptive signal optimization for ISAC signals. This article may provide the guidelines for the research of ISAC signals in 5G-A and 6G mobile communication *** Codes 94-02 Copyright © 2023, The Authors. All rights reserved.

关键词： Orthogonal frequency division multiplexing

Golden grain: Building a secure and decentralized model marketplace for MLaaS

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Weng, Jiasi Weng, Jian Cai, Chengjun Huang, Hongwei Wang, Cong The College of Information Science and Technology College of Cyber security National Joint Engineering Research Center of Network Security Detection and Protection Technology Guangdong Key Laboratory of Data Security and Privacy Preserving Jinan University Guangzhou510632 China The Department of Computer Science City University of Hong Kong Hong Kong Hong Kong The City University of Hong Kong Shenzhen Research Institute Shenzhen518057 China

ML-as-a-service (MLaaS) becomes increasingly popular and revolutionizes the lives of people. A natural requirement for MLaaS is, however, to provide highly accurate prediction services. To achieve this, current MLaaS systems integrate and combine multiple well-trained models in their services. Yet, in reality, there is no easy way for MLaaS providers, especially for startups, to collect sufficiently well-trained models from individual developers, due to the lack of incentives. In this paper, we aim to fill this gap by building up a model marketplace, called as Golden Grain, to facilitate model sharing, which enforces the fair model-money swapping process between individual developers and MLaaS providers. Specifically, we deploy the swapping process on the blockchain, and further introduce a blockchain-empowered model benchmarking process for transparently determining the model prices according to their authentic performances, so as to motivate the faithful contributions of well-trained models. Especially, to ease the blockchain overhead for model benchmarking, our marketplace carefully offloads the heavy computation and designs a secure off-chain on-chain interaction protocol based on a trusted execution environment (TEE), for ensuring both the integrity and authenticity of benchmarking. We implement a prototype of our Golden Grain on the Ethereum blockchain, and conduct extensive experiments using standard benchmark datasets to demonstrate the practically affordable performance of our design. © 2020, CC BY.

关键词： Blockchain