检索结果-内蒙古大学图书馆

Malicious Attacks and Defenses for Deep-Reinforcement-Learning-Based Dynamic Spectrum Access

IEEE INTERNET OF THINGS JOURNAL 2025年第8期12卷 10127-10138页

作者： Wang, Zhaowei Huang, Yunsong Liu, Weicheng Wang, Hui-Ming Xi An Jiao Tong Univ Sch Informat & Commun Engn Key Lab Intelligent Networks & Network Secur Xian 710049 Peoples R China Xi An Jiao Tong Univ Key Lab Intelligent Networks & Network Secur Minist Educ Xian 710049 Peoples R China

Dynamic spectrum access (DSA) is a technology proposed to address issues, such as spectrum scarcity, inflexible spectrum management, and spectrum waste in wireless communication. This is crucial in supporting the escalating demands of spectrum particularly for Internet of Things (IoT)-based applications. Modeling the spectrum access problem as a Markov decision process (MDP) and incorporating deep reinforcement learning (DRL) have emerged as a cutting-edge approach to tackle this challenge. However, the application of DRL in spectrum access is vulnerability to malicious attacks, posing significant security threats. We introduce both glass-box adversarial attack and closed-box jamming attack over-the-air to assess the susceptibility of DRL-based spectrum access system. The simulation results demonstrate the destructive effect of these attack methods in disrupting the spectrum access process of DRL models, adversely affecting the overall performance of communication systems. Moreover, we propose effective defense mechanisms to mitigate potential threats posed by adversary on DRL-based spectrum access. By incorporating advanced defense mechanisms, we successfully enhance the robustness of the system, ensuring the secure and stable operation of the spectrum access system.

关键词： Jamming Wireless communication Closed box Atmospheric modeling Perturbation methods Internet of Things Adaptation models Training Interference Wireless sensor networks Adversarial attack deep reinforcement learning (DRL) dynamic spectrum access (DSA) Internet of Things (IoT) jamming attack Markov decision process (MDP)

来源：评论

学校读者我要写书评

暂无评论

Evading Detection Actively: Toward Anti-Forensics Against Forgery Localization

引用

IEEE TRANSACTIONS ON DEPENDABLE AND securE COMPUTING 2025年第2期22卷 852-869页

作者： Zhuo, Long Luo, Shenghai Tan, Shunquan Chen, Han Li, Bin Huang, Jiwu Shenzhen MSU BIT Univ Guangdong Lab Machine Percept & Intelligent Comp Fac Engn Shenzhen 518116 Peoples R China Shenzhen Key Lab Media Secur Guangdong Key Lab Intelligent Informat Proc Shenzhen 518060 Guangdong Peoples R China

Anti-forensics seeks to eliminate or conceal traces of tampering artifacts. Typically, anti-forensic methods are designed to deceive binary detectors and persuade them to misjudge the authenticity of an image. However, to the best of our knowledge, no attempts have been made to deceive forgery detectors at the pixel level and mis-locate forged regions. Traditional adversarial attack methods cannot be directly used against forgery localization due to the following defects: 1) they tend to just naively induce the target forensic models to flip their pixel-level pristine or forged decisions;2) their anti-forensics performance tends to be severely degraded when faced with the unseen forensic models;3) they lose validity once the target forensic models are retrained with the anti-forensics images generated by them. To tackle the three defects, we propose SEAR (Self-supErvised Anti-foRensics), a novel self-supervised and adversarial training algorithm that effectively trains deep-learning anti-forensic models against forgery localization. SEAR sets a pretext task to reconstruct perturbation for self-supervised learning. In adversarial training, SEAR employs a forgery localization model as a supervisor to explore tampering features and constructs a deep-learning concealer to erase corresponding traces. We have conducted large-scale experiments across diverse datasets. The experimental results demonstrate that, through the combination of self-supervised learning and adversarial learning, SEAR successfully deceives the state-of-the-art forgery localization methods, as well as tackle the three defects regarding traditional adversarial attack methods mentioned above.

关键词： Location awareness Training Forensics Perturbation methods Computational modeling Self-supervised learning Detectors Forgery Adversarial machine learning Robustness Anti-forensics concealer supervisor self-supervised training adversarial learning

来源：评论

学校读者我要写书评

暂无评论

Four-Port Probe Calibration Using 64-Term Error Model for On-Wafer S-Parameter Measurement of Microwave Circuits Up to 110 GHz

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS I-REGULAR PAPERS 2025年

作者： Zhou, Jiefeng Zhang, Ling Chen, Ziyang Li, Da Fan, Jun Li, Er-Ping Zhejiang Univ Coll Informat Sci & Elect Engn Zhejiang Key Lab Intelligent Electromagnet Control Hangzhou 310027 Peoples R China

This article presents a novel four-port probe calibration method for on-wafer S-parameter measurement of microwave circuits and, for the first time, realizes measurement verification up to 110 GHz. The method regards the 64 error terms in the four-port probe calibration as an error matrix, which can be solved by a homogeneous equation system using a generalized scatter matrix theory. The calibration algorithm can consider the crosstalk between the probes and improve the calibration accuracy at high frequencies. This method only requires six calibration standards to complete the four-port probe calibration. Only one coupled differential line with a symmetric structure is needed as the Thru, which replaces the traditional U-shape and asymmetric Thru and effectively reduces the number of calibration standards used in the four-port probe calibration. In addition, the method combined with an optimization method accurately and efficiently calculates the parasitic parameters of the calibration standards at high frequencies. The proposed method is validated by three different devices under test (DUTs) up to 110 GHz. Their S-parameters obtained by the proposed method, including all the pure-mode and mode-conversion terms, have high accuracy in magnitude and phase, proving the correctness and convenience of this method.

关键词： Calibration Probes Scattering parameters Crosstalk Microwave measurement Standards Mathematical models Accuracy Microwave theory and techniques Microwave circuits Calibration standards four-port probe calibration microwave circuits on-wafer S-parameter measurement 64-term error model

来源：评论

学校读者我要写书评

暂无评论

FCFS: A Dual-Channel and Reservation-Based MAC Protocol for Underwater Acoustic Networks

引用

IEEE INTERNET OF THINGS JOURNAL 2025年第4期12卷 3980-3990页

作者： Jin, Xiaocao Liu, Zhixin Ma, Kai Yanshan Univ Hebei Key Lab Ind Comp Control Engn Qinhuangdao 066004 Peoples R China Yanshan Univ Key Lab Intelligent Control & Neural Informat Proc Minist Educ Qinhuangdao 066004 Peoples R China

Designing a pragmatic medium access control (MAC) protocol to operate at low collision rate while providing high throughput is significant for underwater acoustic networks (UANs). Though the centralized control approach could greatly reduce transmission collisions, it normally requires the real-time global network information, such as traffic load, remaining energy, network topology, etc., which is a harsh requirement especially in dynamic UANs. In contrast, the distributed control scheme appears to be more attractive and promising. However, due to the long propagation delay of acoustic signals in the water, the spatiotemporal uncertainty problem and the carrier sensing zone problem in UANs make the distributed MAC protocol unable to avoid frame collisions effectively, which degrades the network performance. For this, we propose an MAC protocol, called FCFS, using the First-Come-First-Served basis, which achieves low frame collision and high network throughput in UANs by adopting the mechanism of medium access reservation via an advance handshaking. Different from the traditional handshake-based protocols, FCFS is good at handling the hidden terminal problem by considering the complete exchange of channel access information among neighboring nodes. Simulation results confirm that the proposed protocol could improve the data reception rate and throughput compared to the related protocols. It also shows that our proposed scheme could maintain a stable performance under different network traffic loads.

关键词： Media Access control Protocols Throughput Sensors Underwater acoustics Spatiotemporal phenomena Internet of Things Bandwidth Propagation delay Network architecture Distributed control high throughput low collision rate (CR) medium access control (MAC) protocol underwater acoustic networks (UANs)

来源：评论

学校读者我要写书评

暂无评论

Nonexistence of generalized bent functions and the quadratic norm form equations

引用

DESIGNS CODES AND CRYPTOGRAPHY 2025年 1-17页

作者： Lv, Chang Zhu, Yuqing Chinese Acad Sci Inst Informat Engn State Key Lab Cyberspace Secur Def Beijing 100093 Peoples R China Beijing Jiaotong Univ Sch Cyberspace Sci & Technol Beijing Key Lab Secur & Privacy Intelligent Transp Beijing 100044 Peoples R China

We present a new result on the nonexistence of generalized bent functions (GBFs) from (Z/tZ)n\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$(\mathbb {Z}/t\mathbb {Z})<^>n$$\end{document} to Z/tZ\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\mathbb {Z}/t\mathbb {Z}$$\end{document} (called type [n, t]) for a large class. Assume p is an odd prime number. By showing certain quadratic norm form equations having no integral points, we obtain a universal result on the nonexistence of GBFs with type [n,2pe]\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$[n, 2p<^>e]$$\end{document} when p and n satisfy a certain inequality, and by computational methods with a widely accepted hypothesis, Generalized Riemann Hypothesis, we also achieve some results on the nonexistence of GBFs for relatively small p.

关键词： Generalized bent functions Quadratic norm form equations Integral points Cyclotomic fields

来源：评论

学校读者我要写书评

暂无评论

Utilizing two subfields to accelerate individual logarithm computation in extended tower number field sieve

引用

DESIGNS CODES AND CRYPTOGRAPHY 2025年 1-17页

作者： Zhu, Yuqing Lv, Chang Liu, Jiqiang Beijing Jiaotong Univ Sch Cyberspace Sci & Technol Beijing Key Lab Secur & Privacy Intelligent Transp Beijing 100044 Peoples R China Chinese Acad Sci Inst Informat Engn State Key Lab Cyberspace Secur Def Beijing 100093 Peoples R China

The hardness of discrete logarithm problem (DLP) over finite fields forms the security foundation of many cryptographic schemes. When the characteristic is not small, the state-of-the-art algorithms for solving the DLP are the number field sieve (NFS) and its variants. NFS first computes the logarithms of the factor base, which consists of elements of small norms. Then, for a target element, its logarithm is calculated by establishing a relation with the factor base. Although computing the factor-base elements is the most time-consuming part of NFS, it can be performed only once and treated as pre-computation for a fixed finite field when multiple logarithms need to be computed. In this paper, we present a method for accelerating individual logarithm computation by utilizing two subfields. We focus on the case where the extension degree of the finite field is a multiple of 6 within the extended tower number field sieve framework. Our method allows for the construction of an element with a lower degree, while maintaining the same coefficient bound compared to Guillevic's method, which uses only one subfield. Consequently, the element derived from our approach enjoys a smaller norm, which will improve the efficiency in individual logarithm computation.

关键词： Discrete logarithm problem Number field sieve Individual logarithm Finite fields

来源：评论

学校读者我要写书评

暂无评论

Unifying Motion and Appearance Cues for Visual Tracking via Shared Queries

引用

IEEE TRANSACTIONS ON CIRCUITS AND SYSTEMS FOR VIDEO TECHNOLOGY 2025年第3期35卷 1987-1998页

作者： Xue, Chaocan Zhong, Bineng Liang, Qihua Xia, Haiying Song, Shuxiang Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Peoples R China Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China

The rich motion and appearance cues between consecutive frames are crucial for robust visual tracking. However, most existing tracking methods are still limited in designing different components to separately employ corresponding cues and even ignore one of them. This makes them difficult to maintain effective interaction between different cues, thus hindering the models from fostering a comprehensive understanding of the target objects. To address these issues, we propose a unified spatio-temporal cues learning framework (named USCLTrack) that comprehensively mines the variation patterns of targets between consecutive frames in complex video streams. Specifically, USCLTrack firstly aggregates motion and appearance cues into shared queries to provide the bridge of interaction between both cues. Then, it directly generates object locations on the condition of these shared queries in an autoregressive manner, unifying different cues to guide future inferences. To effectively learn multiple spatio-temporal cues aggregated in the shared queries, we develop a spatio-temporal attention mechanism. This mechanism integrates motion cues with appearance cues according to the time steps for ensuring temporal consistency. Moreover, it concurrently captures motion trends and appearance changes to facilitate the understanding of the target objects. Extensive experiments on eight popular tracking benchmarks validate the effectiveness of the proposed USCLTrack.

关键词： Tracking Target tracking Transformers Visualization Market research Decoding Trajectory Feature extraction Object tracking Location awareness Visual tracking spatiao-temporal cues motion trends appearance changes

来源：评论

学校读者我要写书评

暂无评论

PF-DETR: Instance position and local feature enhancement for DETR

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2025年 1-16页

作者： Zhong, Xinfang Kuang, Wenlan Li, Zhixin Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Peoples R China Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China

The recently proposed DEtection TRansformer (DETR) and its variants have achieved good performance in end-to-end object detection. However, these methods do not take into account the positional relationships between instances in the image and the importance of local feature information. To this end, this paper proposes an object detection method based on instance position and local feature enhancement, named PF-DETR. Firstly, a Dual Positional Encoding Attention (DPEA) is designed, which can simultaneously embed the absolute and relative position information of the object queries, thereby enhancing the localization ability of the queries. Secondly, we introduce a Local Feature Enhancement Module (LFEM), which makes full use of local information to enrich and refine object queries, further enhancing the queries' perception of local features. Finally, a positional relation is established between the queries and the encoded image feature, and a Positional Interaction Cross-Attention (PICA) is proposed to allow the queries to find relevant regions in the encoded image feature more quickly. The experimental results on the MS COCO 2017 dataset show that the proposed method can effectively improve the convergence and performance of the model.

关键词： Object detection DETR Vision transformer Local feature Positional relationship

来源：评论

学校读者我要写书评

暂无评论

A novel Dual-Branch Generative Adversarial Network for electrocardiogram data generation

引用

DIGITAL SIGNAL PROCESSING 2025年 162卷

作者： Zhou, Feiyan Huang, Tianlong Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Peoples R China Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China

Computer-assisted electrocardiogram (ECG) analysis is vital for the clinical diagnosis of cardiovascular diseases. However, the performance of many ECG classification methods is adversely affected by data imbalance. Generative Adversarial Networks (GANs) have recently emerged as a promising approach to address this challenge. Nevertheless, existing GAN models for ECG generation typically utilize a single generator structure, which limits their ability to generate complex ECG waveforms. To address this limitation, this paper proposes a novel dual-branch GAN model that integrates the strengths of Transformer and Long Short-Term Memory (LSTM) networks, along with self-attention mechanisms, to enhance the quality of ECG generation. The effectiveness of the proposed method was validated using the internationally recognized MIT-BIH Arrhythmia Database (MITBIH-AR) and the Chinese Cardiovascular Disease Database (CCDD). By incorporating the ECG data generated by the proposed model into the training set, the classification accuracy on the MIT-BIH-AR database for four diseases improved from 90.98 % to 96.66 %. Similarly, the classification accuracy for ventricular premature beats on the CCDD increased from 98.51 % to 99.34 %. The experimental results demonstrate that the proposed generative model can produce more realistic ECG data, thereby enhancing the performance of subsequent classification tasks.

关键词： ECG Data Imbalance Generative Adversarial Networks Transformer Long Short-Term Memory Networks Self-Attention Mechanism

来源：评论

学校读者我要写书评

暂无评论

引用

MULTIMEDIA SYSTEMS 2025年第1期31卷 1-15页

作者： Liu, Mingqi Li, Zhixin Guangxi Normal Univ Key Lab Educ Blockchain & Intelligent Technol Minist Educ Guilin 541004 Peoples R China Guangxi Normal Univ Guangxi Key Lab Multisource Informat Min & Secur Guilin 541004 Peoples R China

Multimodal sentiment analysis (MSA) aims to predict human emotions via language, visual and acoustic modalities. Based on the idea of extracting modalities into modality-invariant and modality-specific components, feature decomposition methods decompose features into similarity and dissimilarity features. However, dissimilarity features contribute less than similarity features due to emotional divergence. And they have not been effectively utilized due to insufficient methods for feature extraction and processing. To address these issues, we propose a dissimilarity feature-driven decomposition network (DFDDN) for MSA. We deploy a feature extraction module to extract and enhance features. This not only increases the differences between the features, but also enables us to focus more on the emotional information contained in the features. We utilize different encoders to decompose features, and design loss functions to increase the differences of modality features. Compared to state-of-the-art (SOTA) method on the CMU-MOSI dataset, there are improvements of 0.35%/1.57% and 0.28%/2.09% in Acc2 and macro F1, a 3.31% improvement in Acc7, and the MAE decreases by 0.1. Compared to SOTA method on the CMU-MOSEI dataset, there is an improvement of 1.34% in Acc7, the Corr increases by 0.016, and the MAE decreases by 0.005.

关键词： Multimodal sentiment analysis Multi-task learning Representation learning Contrastive learning Feature decomposition

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：