检索结果-内蒙古大学图书馆

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Runkai Zheng Rongjun Tang Jianze Li Li Liu School of Data Science The Chinese University of Hong Kong Shenzhen School of Science and Engineering The Chinese University of Hong Kong Shenzhen Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen

ISBN: (纸本)9781713871088

Convolutional neural networks (CNN) can be manipulated to perform specific behaviors when encountering a particular trigger pattern without affecting the performance on normal samples, which is referred to as backdoor attack. The backdoor attack is usually achieved by injecting a small proportion of poisoned samples into the training set, through which the victim trains a model embedded with the designated backdoor. In this work, we demonstrate that backdoor neurons are exposed by their pre-activation distributions, where populations from benign data and poisoned data show significantly different moments. This property is shown to be attack-invariant and allows us to efficiently locate backdoor neurons. On this basis, we make several proper assumptions on the neuron activation distributions, and propose two backdoor neuron detection strategies based on (1) the differential entropy of the neurons, and (2) the Kullback-Leibler divergence between the benign sample distribution and a poisoned statistics based hypothetical distribution. Experimental results show that our proposed defense strategies are both efficient and effective against various backdoor attacks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Activity Detection and Channel Estimation in Massive Machine-Type Communications with Low-Resolution ADC

Joint Activity Detection and Channel Estimation in Massive M...

引用

IEEE International Conference on Communications (ICC)

作者： Ye Xue An Liu Yang Li Qingjiang Shi Vincent Lau Shenzhen Research Institute of Big Data Shenzhen China College of Information Science and Electronic Engineering Zhejiang University Hangzhou China Tongji University Shanghai China Dept. of ECE The Hong Kong University of Science and Technology Hong Kong

In massive machine-type communications, data transmission is usually considered sporadic, and thus inherently has a sparse structure. This paper focuses on the joint activity detection (AD) and channel estimation (CE) problems in massive-connected communication systems with low-resolution analog-to-digital converters. To further exploit the sparse structure in transmission, we propose a maximum posterior probability (MAP) estimation problem based on both sporadic activity and sparse channels for joint AD and CE. Moreover, a majorization-minimization-based method is proposed for solving the MAP problem. Finally, various numerical experiments verify that the proposed scheme outperforms state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Using Meta-Heuristic Methods to Detect Botnet Attacks in Internet of Things

SSRN

引用

SSRN 2023年

作者： Mardani, Shayan Boroujeni, Farsad Zamani Akbari, Mehdi Department of Engineering Sepahan Institute of Higher Education Science and Technology Iran Department of Computer Engineering Islamic Azad University Science and Research Branch Tehran Iran Faculty of Computer Engineering Islamic Azad University Najafabad Branch Najafabad Iran Big Data Research Center Islamic Azad University Najafabad Branch Najafabad Iran

The need for timely detection of botnet attacks due to the increase in the number of Internet of Things devices is very necessary to minimize security risks and ensure network security. Recently, botnet attack detection methods are based on artificial intelligence techniques;And in order to deal with the growing dimensions of Internet of Things data, they have used various filtering and wrapping feature selection methods. In this paper, for the challenge of IoT data dimensions in detecting botnet attacks, a comparison has been made between 7 different old and new meta-heuristic methods including PSO, Giza, RSO, Firefly, PEC, BAT and GWO. In this model, decision tree algorithm is used to detect attacks. The experimental results of the methods on two data sets IOT-BotNet and N-BaIoT show that all meta-heuristic methods in binary classification have similar performance and have been able to achieve accuracy above 99%. In detecting the type of attacks (multi-class classification), the results show that the best performance belongs to RSO, Giza, which reached an accuracy of over 99% and are among the latest meta-heuristic methods. The results of the methods show that meta-heuristic feature selection algorithms can effectively reduce data dimensions;So that the accuracy of the proposed attack detection model has increased compared to previous methods. © 2023, The Authors. All rights reserved.

关键词： Botnet

来源：评论

学校读者我要写书评

暂无评论

A Graph Learning Framework for Prediction of Missing Landmines Using Airborne Magnetometry in Iot Environment

SSRN

引用

SSRN 2023年

作者： Barnawi, Ahmed Kumar, Krishan Kumar, Neeraj Alzahrani, Bander Almansour, Amal The Department of Computing and IT King Abdulaziz University Jeddah Saudi Arabia The KAU Cloud Computing and Big Data Research Group Saudi Arabia The Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Deemed to be University Punjab Patiala India

The continued use of landmines and the presence of already deployed landmines endanger countless lives worldwide. Detecting the landmines is a challenging task as it includes carefully surveying the target region using a suitable sensing device. One of the most trending sensory methods is the magnetometer sensing. The magnetometer sensor is used to visualize magnetic anomalies by measuring the magnetic field strength of magnetized objects especially in IoT environment. The process can be automated using a UAV-based survey by applying signal processing and computer vision techniques using the captured images. However, airborne magnetic detection fails to detect some of the landmines due to environmental conditions, thus the technology utilization is limited. On the other hand, the missing magnetic signature of some mines poses a severe risk to the mine removal team and civilians as they can be accidentally triggered. The work proposed is a further development of ongoing effort to come up with automated detection system. This paper focuses on post processing of magnetometry signature image of landmines deployed as rows in minefields, where mines are deployed in mu+++++ltiple rows patterns. The framework includes (1) a graph-based approach to identify the row clusters present in the pattern, (2) identify the row’s discontinuities and (3) localize the missing signatures via interpolation. A simulated dataset is used to test and evaluate the proposed strategies. The results signify the adequate performance of the proposed method in the identification of missing magnetic signatures of row pattern deployments which enhances reliability of the automatic airborne magnetic sensing of landmines. © 2023, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Predicting response to patients with gastric cancer via a dynamic-aware model with longitudinal liquid biopsy data

引用

Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association 2025年 2025 Jun 17页

作者： Zifan Chen Jie Zhao Yanyan Li Xujiao Feng Yang Chen Yilin Li Xinyu Nan Huimin Liu Bin Dong Lin Shen Li Zhang Center for Data Science Peking University Haidian District Beijing 100080 China. National Engineering Laboratory for Big Data Analysis and Applications Peking University Beijing China. Peking University Changsha Institute for Computing and Digital Economy Changsha China. Department of Gastrointestinal Oncology Key Laboratory of Carcinogenesis and Translational Research (Ministry of Education) Peking University Cancer Hospital and Institute Beijing China. Guangzhou Medical University Guangzhou China. Beijing International Center for Mathematical Research and the New Cornerstone Science Laboratory Peking University Beijing China. Center for Machine Learning Research Peking University Beijing China. Center for Data Science Peking University Haidian District Beijing 100080 China. zhangli_pku@***.

BACKGROUND:Gastric cancer (GC) presents challenges in predicting treatment responses due to its patient-specific heterogeneity. Recently, liquid biopsies have emerged as a valuable data modality, offering essential cellular and molecular insights while facilitating the capture of time-sensitive information. This study aimed to leverage artificial intelligence (AI) technology to analyze longitudinal liquid biopsy data. METHODS:We collected a dataset from longitudinal liquid biopsies of 91 patients at Peking Cancer Hospital, spanning from July 2019 to April 2022. This dataset included 1895 tumor-related cellular images and 1698 tumor marker indices. Subsequently, we introduced the Dynamic-Aware Model (DAM) to predict responses to GC treatment. DAM incorporates dynamic data through AI-engineered components, facilitating an in-depth longitudinal analysis. RESULTS:Utilizing threefold cross-validation, DAM exhibited superior performance compared to traditional cell-counting methods, achieving an AUC of 0.807 in predicting GC treatment responses. In the test set, DAM maintained stable efficacy with an AUC of 0.802. Besides, DAM showed the capability to accurately predict treatment responses based on early treatment data. Moreover, DAM's visual analysis of attention mechanisms identified six dynamic visual features related to focus areas, which were strongly associated with treatment-response. CONCLUSIONS:These findings represent a pioneering effort in applying AI technology to interpret longitudinal liquid biopsy data and employ visual analytics in GC. This approach provides a promising pathway toward precise response prediction and personalized treatment strategies for patients with GC.

关键词： Artificial intelligence Deep learning Gastric cancer Longitudinal liquid biopsy data Treatment response prediction

来源：评论

学校读者我要写书评

暂无评论

Transient Session Key Derivation Protocol for Key Escrow Prevention in Public Key Infrastructure 1st

Transient Session Key Derivation Protocol for Key Escrow Pre...

引用

1st EAI International Conference on Internet of Everything, IoECon 2022

作者： Nyangaresi, Vincent Omollo Abduljabbar, Zaid Ameen Maolood, Ismail Yaqub Sibahee, Mustafa A. Al Ma, Junchao Aldarwish, Abdulla J. Y. Faculty of Biological and Physical Sciences Tom Mboya University Homabay40300 Kenya Department of Computer Science College of Education for Pure Sciences University of Basrah Basrah61004 Iraq Shenzhen Institute Huazhong University of Science and Technology Shenzhen518118 China – System Information Ministry of Higher Education and Scientific Research Erbil Iraq College of Big Data and Internet Shenzhen Technology University Shenzhen518118 China Computer Technology Engineering Department Iraq University College Basrah Iraq

ISBN: (纸本)9783031252211

The Internet of Things (IoT) devices have been deployed to realize smart environments such as smart cities, smart homes, smart health and smart grids. In these domains, the IoT devices collect and forward high volumes of sensitive and private data. It is therefore important that security schemes be developed to protect the exchanged data. In this regard, a myriad of authentication protocols have been developed over the recent past. However, these schemes deploy cryptographic primitives that result in extremely high communication, storage and computation complexities. In addition, some of these protocols still have numerous security and privacy issues that render them unsuitable for deployment in an IoT environment. For instance, untraceability, anonymity, key escrow problems and attack vectors such as de-synchronization and forgery attacks are frequently ignored. In this paper, a transient session key derivation protocol is developed to address some of these security and efficiency challenges. The security analysis executed shows that this protocol offers untraceability, device anonymity and perfect forward key secrecy. In addition, it is robust against de-synchronization, known secret key leakage, eavesdropping and forgery attacks. In terms of operational efficiency, this protocol incurs the lowest computation and communication complexities. © 2023, ICST institute for Computer sciences, Social Informatics and Telecommunications engineering.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

GESH-NET: GRAPH-ENHANCED SPHERICAL HARMONIC CONVOLUTIONAL NETWORKS FOR CORTICAL SURFACE REGISTRATION

arXiv

引用

arXiv 2024年

作者： Zhang, Ruoyu Wang, Lihui Tang, Kun Xu, Jingwen Wei, Hongjiang Engineering Research Center of Text Computing & Cognitive Intelligence Ministry of Education Key Laboratory of Intelligent Medical Image Analysis and Precise Diagnosis of Guizhou Province State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang550025 China School of Biomedical Engineering Shanghai Jiao Tong University Shanghai China

Cortical surface registration plays a crucial role in coordinating individual cortical functions and anatomical features, serving as a fundamental step in cortical surface analysis. Its aim is to align the anatomical or functional regions of different individuals, which is of great importance for neuroimaging studies across different populations. Currently, cortical surface registration techniques based on classical methods have been well developed. However, a key issue with classical registration methods is that for each pair of images to be registered, it is necessary to search for the optimal transformation in the deformation space according to a specific optimization algorithm until the similarity measure function converges, which cannot meet the requirements of real-time and high-precision in medical image registration. With the spectacular success of deep learning in the field of computer vision, researching cortical surface image registration techniques based on deep learning models has become a new direction. But so far, there are still only a few studies on cortical surface image registration based on deep learning. Moreover, although deep learning methods theoretically have stronger representation capabilities, surpassing the most advanced classical methods in registration accuracy and distortion control remains a challenge. Therefore, to address this challenge, this paper constructs a deep learning model to study the technology of cortical surface image registration. The specific work is as follows: (1) An unsupervised cortical surface registration network based on a multi-scale cascaded structure is designed, and a convolution method based on spherical harmonic transformation is introduced to register cortical surface data. This solves the problem of scale-inflexibility of spherical feature transformation and optimizes the multi-scale registration process. The results show that the proposed network outperforms the other deep learning-based registration m

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

USED: Universal Speaker Extraction and Diarization

arXiv

引用

arXiv 2023年

作者： Ao, Junyi Yıldırım, Mehmet Sinan Tao, Ruijie Ge, Meng Wang, Shuai Qian, Yanmin Li, Haizhou Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore119077 Singapore Saw Swee Hock School of Public Health National University of Singapore Singapore117549 Singapore Shenzhen Research Institute of Big Data Shenzhen518172 China Auditory Cognition and Computational Acoustics Lab Department of Computer Science and Engineering China MoE Key Laboratory of Artificial Intelligence AI Institute Shanghai Jiao Tong University Shanghai200240 China

Speaker extraction and diarization are two enabling techniques for real-world speech applications. Speaker extraction aims to extract a target speaker’s voice from a speech mixture, while speaker diarization demarcates speech segments by speaker, annotating ‘who spoke when’. Previous studies have typically treated the two tasks independently. In practical applications, it is more meaningful to have knowledge about ‘who spoke what and when’, which is captured by the two tasks. The two tasks share a similar objective of disentangling speakers. Speaker extraction operates in the frequency domain, whereas diarization is in the temporal domain. It is logical to believe that speaker activities obtained from speaker diarization can benefit speaker extraction, while the extracted speech offers more accurate speaker activity detection than the speech mixture. In this paper, we propose a unified model called Universal Speaker Extraction and Diarization (USED) to address output inconsistency and scenario mismatch issues. It is designed to manage speech mixtures with varying overlap ratios and variable number of speakers. We show that the USED model significantly outperforms the competitive baselines for speaker extraction and diarization tasks on LibriMix and SparseLibriMix datasets. We further validate the diarization performance on CALLHOME, a dataset based on real recordings, and experimental results indicate that our model surpasses recently proposed approaches. Copyright © 2023, 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

Weak Signal Detection based on Beta Divergence

Weak Signal Detection based on Beta Divergence

引用

IEEE Workshop on Signal Processing Advances in Wireless Communications (SPAWC)

作者： Jiahao Liu Haoxuan Liu Wenqiang Pu Rui Zhou Ming-Yi You Qingjiang Shi Science and Technology on Communication Information Security Control Laboratory Jiaxing China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen China School of Software Engineering Tongji University Shanghai China

Among different electromagnetic spectrum monitoring tasks, a fundamental one is detecting the presence of weak communication signal under non-cooperative setting. Various detection methods have been studied in the literature. These detection methods usually construct a proper hypothesis testing metric to distinguish the signal-plus-noise and noise-only signals. Information entropy based metric has recently been studied and shown its superiority over traditional energy based metrics. We find that it can be explained as a realization of the general Kullback-Leibler divergence. Inspired by that, in this paper, we propose to detect the signal using a statistic divergence called β-divergence. Different choices of β will lead to several well known divergences, e.g., Itakura-Saito divergence and Euclidean distance. We study its detection performance for non-cooperative signal sources. Both simulation and real experiments demonstrate that β-divergence can improve detection performance for various modulation types of communication signals.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Target-Mounted intelligent Reflecting Surface for Secure Wireless Sensing

arXiv

引用

arXiv 2023年

作者： Shao, Xiaodan Zhang, Rui The School of Science and Engineering Chinese University of Hong Kong Shenzhen518172 China School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

In this paper, we consider a challenging secure wireless sensing scenario where a legitimate radar station (LRS) intends to detect a target at unknown location in the presence of an unauthorized radar station (URS). We aim to enhance the sensing performance of the LRS and in the meanwhile prevent the detection of the same target by the URS. Under this setup, conventional stealth-based approaches such as wrapping the target with electromagnetic wave absorbing materials are not applicable, since they will disable the target detection by not only the URS, but the LRS as well. To tackle this challenge, we propose in this paper a new target-mounted IRS approach, where intelligent reflecting surface (IRS) is mounted on the outer/echo surface of the target and by tuning the IRS reflection, the strength of its reflected radar signal in any angle of departure (AoD) can be adjusted based on the signal’s angle of arrival (AoA), thereby enhancing/suppressing the signal power towards the LRS/URS, respectively. To this end, we propose a practical protocol for the target-mounted IRS to estimate the LRS/URS channel and waveform parameters based on its sensed signals and control the IRS reflection for/against the LRS/URS accordingly. Specifically, we formulate new optimization problems to design the reflecting phase shifts at IRS for maximizing the received signal power at the LRS while keeping that at the URS below a certain level, for both the cases of short-term and long-term IRS operations with different dynamic reflection capabilities. To solve these non-convex problems, we apply the penalty dual decomposition method to obtain high-quality suboptimal solutions for them efficiently. Finally, simulation results are presented that verify the effectiveness of the proposed protocol and algorithms for the target-mounted IRS to achieve secure wireless sensing, as compared with various benchmark schemes. © 2023, CC BY.

关键词： Beamforming

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：