检索结果-内蒙古大学图书馆

SIGFinger: A Subtle and Interactive GNN Fingerprinting Scheme via Spatial Structure Inference Perturbation

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Jia, Ju Li, Renjie Wu, Cong Ma, Siqi Wang, Lina Deng, Robert H. Southeast University School of Cyber Science and Engineering Nanjing210096 China Nanyang Technological University School of Computer Science and Engineering 639798 Singapore University of New South Wales School of Engineering and Information Technology CanberraACT2612 Australia Wuhan University Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan430072 China Singapore Management University School of Information Systems 188065 Singapore

There have been significant improvements in intellectual property (IP) protection for deep learning models trained on Euclidean data. However, the complex and irregular graph-structured data in non-Euclidean space poses a huge challenge to the IP protection of graph neural networks (GNNs). To address this issue, we propose a subtle and interactive GNN fingerprinting scheme through spatial structure inference perturbation, which captures the stable coordination patterns of fingerprint to guarantee the reliability of copyright verification. Specifically, the data augmentation based on adaptive graph diffusion is first exploited to generate more samples, which enables the exploration of fingerprint information from coarse to fine. Subsequently, the graph-structured data are manipulated by multi-constrained spectral clustering to analyze intrinsic and extrinsic structure correlations in a causal inference manner. Ultimately, the cycle-consistent statistical optimization is performed to determine the copyright of GNN models from both intra-graph and inter-graph perspectives. Extensive experiments show that our proposed scheme can effectively verify the IP of GNN models on various challenging graph-structured datasets. Furthermore, we reveal that the space causality inference can facilitate the acquisition of inherent structural information, which improves the quality and robustness of the fingerprint under model modification operations and other model stealing attacks. © 2004-2012 IEEE.

关键词： causal inference GNN fingerprinting IP protection quality and robustness stable structure knowledge

来源：评论

学校读者我要写书评

暂无评论

Deep learning enhanced prediction of microwave dielectric constant of spinel ceramics eliminating manual feature engineering

引用

Materials Today Physics 2025年 54卷

作者： Liu, Xiaobin Huang, Qiuxia Su, Chang Shao, Ning Zhang, Lei Tian, Yapeng Zhou, Huanfu College of Physics and Electronic Information Engineering Guilin University of Technology Guilin514004 China College of Computer Science and Engineering Guilin University of Technology Guilin514004 China Guangxi Key Laboratory of Embedded Technology and Intelligent Systems Guilin University of Technology Guilin514004 China Henan Institute of Advanced Technology College of Materials Science and Engineering Zhengzhou University Zhengzhou450003 China School of Materials Science and Engineering Guilin University of Technology Guilin514004 China

Machine learning (ML) has demonstrated considerable promise and superiority in the prediction of microwave dielectric ceramic (MWDC) properties. Nonetheless, applying traditional ML models often requires processing numerous features, making their implementation complex and unwieldy. In this work, a deep learning (DL) model named CRANCNN-M2V that predicts the dielectric constant of spinel-MWDCs eliminating manual feature engineering has been constructed. The model can identify essential features directly from chemical compositions using the data embedding method. Our model further improved the network based on a Compositionally Restricted Attention-based Neural Network (CrabNet) and showed the enhanced prediction performance in the dielectric constant of spinel-MWDCs, achieving an RMSE of 1.52, an MAE of 0.938, and an R2 of 0.954, and it also outperformed commonly used traditional ML models (e.g., XGBoost, Random Forest (RF), Decision Tree (DT), etc.). Furthermore, the contribution of different elements in the dielectric constant of spinel MWDCs has been analyzed via our CRANCNN-M2V model. Highly accurate and efficient prediction of our model will effectively promote the design and development of spinel-MWDCs applied for wireless communication. © 2025 Elsevier Ltd

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Many-Problem Surrogates for Transfer Evolutionary Multiobjective Optimization With Sparse Transfer Stacking

引用

IEEE Transactions on Evolutionary Computation 2025年

作者： Li, Hao Wan, Fanggao Gong, Maoguo Qin, A.K. Wu, Yue Xing, Lining Xidian University School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Shaanxi Province Xi'an710071 China Inner Mongolia Normal University School of Electronic Engineering Key Laboratory of Collaborative Intelligence Systems Ministry of Education Xidian University Xi'an China and Academy of Artificial Intelligence College of Mathematics Science Hohhot China Swinburne University of Technology Department of Computing Technologies HawthornVIC3122 Australia Xidian University School of Computer Science and Technology Xi'an710071 China

For expensive multiobjective optimization problems, there exists useful knowledge, e.g., the trained surrogate models, can be transferred to assist the optimization of a target optimization problem, which is termed as multi-problem surrogates. Stacking transfer is able to combine the pretrained source surrogate models and the preliminary target model with a meta-regression algorithm to transfer knowledge from source to target. However, when large-scale source models are involved in the many-problem scenarios, the less correlated sources may hurt the target performance, which is known as negative transfer. In this paper, sparse representation of the coefficients of meta-regression is considered to automatically select the most relevant source models for largely avoiding negative transfer. In the proposed many-problem surrogates, the coefficients of the source and target models are assumed to be sparse under the non-negativity and sum-to-one constraints. Then a sparse transfer stacking model is established with l1-norm of the coefficients. Next, the alternating direction method of multipliers is employed to solve the resulting constrained optimization problem by converting it into several much simpler problems. Most of the previous works assume that the costs for evaluation have no much difference and this assumption rarely holds in the real-world applications. In order to further reduce the total costs, an improved surrogate model with a cost-sensitive measure is designed to estimate the cost and select new solutions for real evaluation based on their estimated fitness, uncertainty and cost. Experimental results on synthetic and practical problems have demonstrated the superiority of the proposed many-problem surrogates. © 1997-2012 IEEE.

关键词： Multiobjective optimization sparse representation surrogate-assisted evolutionary algorithm transfer stacking

来源：评论

学校读者我要写书评

暂无评论

Innate Cyber-Immunity and Acquired Cyber-Immunity across Multi-Area Power systems

引用

IEEE Transactions on Power systems 2025年

作者： Hou, Jiazuo Song, Yue Hou, Yunhe Peng, Jimmy Chih-Hsien National University of Singapore Department of Electrical and Computer Engineering Singapore Tongji University Department of Control Science and Engineering National Key Laboratory of Autonomous Intelligent Unmanned Systems Shanghai Institute of Intelligent Science and Technology Shanghai201804 China The University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong University of Hong Kong Shenzhen Institute of Research and Innovation Shenzhen518057 China

Organisms have evolved innate and acquired immune systems to defend against pathogens like coronaviruses. Similarly, power networks, threatened by cyber-attacks, desire cyber-immunity. Inspired by the immunology research, this study develops a cyber-immune strategy-characterizing innate cyber-immunity and establishing acquired cyber-immunity-for any selected portion of a power network (termed as power subnetwork) against stealthy false data injection (FDI) cyberattacks. Therein, without extrinsic protection and information asymmetry, this paper for the first time confirms the existence and provides closed-form conditions for power subnetworks that are innately immune to FDI cyber-attacks despite all measurements being compromised. Single-leader-multi-follower bi-level optimization models are then developed to strategically allocate measurement protection, leading to the acquired cyber-immunity, whose conditions for existence and the least cost are explicitly formulated. More importantly, a bi-directional cyber-immunity propagation mechanism is presented to provide the optimal spatial allocation of defense resources across adjacent subnetworks. It also explicitly determines the temporal allocation sequence, revealing its sequential and cumulative impacts on establishing cyber-immunity. This is achieved by designing recursive traversal algorithms, one of which is modelled as a post-order depth-first-search problem of a multi-fork tree. The proposed subnetwork-specific cyber-immune strategy is verified in a modified Australian National Electricity Market. © 1969-2012 IEEE.

关键词： Phishing

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Radiomics Analysis for Prostate Cancer Detection Harnessing Machine and Deep Learning Models

Large-Scale Radiomics Analysis for Prostate Cancer Detection...

引用

IEEE International Symposium on Biomedical Imaging

作者： Eugenia Mylona Dimitrios I. Zaridis Charalampos N. Kalantzopoulos Vasileios C. Pezoulas Nikolaos S. Tachos George K. Matsopoulos Daniele Regge Nikolaos Papanikolaou Manolis Tsiknakis Kostas Marias Dimitrios I. Fotiadis Biomedical Research Institute FORTH Ioannina Greece Unit of Medical Technology Intelligent Information Systems University of Ioannina Greece Biomedical Engineering Laboratory School of Electrical & Computer Engineering National Technical University of Athens Greece Institute of Computer Science FORTH Heraklion Greece Department of Radiology Candiolo Cancer Institute FPO-IRCCS Strada Provinciale Candiolo Italy Computational Clinical Imaging Group Champalimaud Foundation Portugal Computational Biomedicine Laboratory Institute of Computer Science FORTH Heraklion Greece Department of Electrical and Computer Engineering Hellenic Mediterranean University Heraklion Greece

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Prostate cancer (PCa) is the second most common cancer in men, making early detection crucial for effective treatment. This study explores the efficacy of machine learning (ML) and deep learning (DL) models in detecting PCa lesions using radiomics features derived from multiparametric MRI data. Leveraging a dataset of 7621 retrospective and 2132 prospective cases from 12 clinical centers across Europe, we compared the performance of various ML (LASSO, Random Forest, SVM, XGBoost) and DL models (CNN, MLP, Transformer, CNN&MLP). Radiomic features were extracted and refined through a robust feature selection process. Models' performance was evaluated through nested cross-validation (CV) and externally. The CNN&MLP model achieved the highest ROC AUC (0.86) and PR AUC (0.90) in CV, while LASSO showed consistent generalization in external validation. Our findings indicate that DL models excel in high-dimensional data analysis but face challenges in generalizing to external datasets, highlighting the importance of external validation for clinical applicability.

关键词： Deep learning Support vector machines Analytical models Biological system modeling Feature extraction Transformers Lesions Prostate cancer Radiomics Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Active RIS-Aided Massive MIMO With Imperfect CSI and Phase Noise

引用

IEEE Transactions on Wireless Communications 2025年

作者： Peng, Zhangjie Zhu, Jianchen Pan, Cunhua Zhang, Zaichen Da Costa, Daniel Benevides Elkashlan, Maged Karagiannidis, George K. Shanghai Normal University College of Information Mechanical and Electrical Engineering Shanghai200234 China Southeast University National Mobile Communications Research Laboratory Nanjing210096 China Interdisciplinary Research Center for Communication Systems and Sensing Department of Electrical Engineering Dhahran31261 Saudi Arabia Queen Mary University of London School of Electronic Engineering and Computer Science LondonE1 4NS United Kingdom Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Greece Artificial Intelligence and Cyber Systems Research Center Lebanon

As a recently proposed reconfigurable intelligent surface (RIS) architecture, active RIS has drawn considerable interest. The important feature of the active RIS is its ability to strengthen the impinging signals to mitigate the multiplicative fading effect inherent in passive RIS-aided systems. Herein, we explore the performance of an active RIS-aided uplink multi-user massive multiple-input multiple-output (MIMO) system, considering the phase noise at the RIS. Furthermore, a two-timescale scheme is utilized, where the base station (BS) beamforming is designed based on the instantaneous aggregated channel state information (CSI), while the statistical CSI is used for designing the phase shifts of the active RIS. In addition, the linear minimum mean square error (LMMSE) estimator is adopted to estimate the aggregated channel, which combines both the cascaded and direct channels. According to the estimated channel, a closedform expression for the lower bound of achievable rate is derived. Based on the theoretical expressions, the power scaling laws for the considered system are also investigated. Specifically, when each user’s transmit power is proportionally reduced by the quantity of BS antennas M or RIS elements N, we find that the amplified thermal noise causes the lower bound of the achievable rate to approach zero as M or N tends to infinity. Moreover, an optimization approach based on a genetic algorithm (GA) is introduced to obtain the optimal phase shifts for maximizing the achievable rate. Numerical results reveal that the active RIS can greatly enhance the performance of the massive MIMO system compared to its passive counterpart. © 2002-2012 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Over-the-Air Computation for Federated Generative Model Fine-Tuning in Unmanned Vehicle-Assisted Disaster Relief

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Zhao, Yikun Feng, Lei Zhou, Fanqin Li, Wenjing Xiong, Zehui Du, Hongyang Wu, Celimuge Guo, Song Quek, Tony Q.S Han, Zhu State Key Laboratory of Networking and Switching Technology Beijing100876 China Singapore University of Technology and Design Information Systems Technology and Design Pillar Singapore487372 Singapore University of Hong Kong Department of Electrical and Electronic Engineering Pok Fu Lam Hong Kong University of Electro-Communications Meta-Networking Research Center Tokyo Japan Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

The utilization of emergent generative artificial intelligence (GAI) within the realm of unmanned vehicles (UVs) can boost edge intelligence and potentially enhance the efficiency and effectiveness of rescue operations. However, to facilitate specialized generative edge intelligence in dynamic UV networks, GAI models need to tap into local data and conduct online fine-tuning, and the dispersed distribution of UVs makes distributed fine-tuning paradigms crucial. Although the federated generative model fine-tuning brings a potential solution, the large number of parameter transmissions involved in its fine-tuning process are often constrained by communication bottlenecks, which are more pronounced for resource-constrained UV networks. To cope with these challenges, we introduce an energy-efficient GAI model fine-tuning framework for the hierarchical UV networks, which employs over-the-air technology to save computational resource costs for unmanned aerial vehicle (UAV) during federated aggregation within a federated learning paradigm. Thereafter, we study the resource allocation problem in the fine-tuning process of the generative model and formulate a joint optimization problem for the bandwidth allocation, power control, computation resource allocation, and denoising factor control, aiming to minimize the system energy consumption. Then, we decouple the original problem into four tractable subproblems, and propose a block coordinate descent algorithm to solve them iteratively. Particularly, we derive a closed-form solution for the denoising factor to minimize the local model uploading transmission energy consumption under a specific AirComp communication error threshold. Simulation based on the state-of-the-art generative models shows that our AirComp-assisted federated generative model fine-tuning scheme can achieve satisfactory customized field-of-view image generation capability compared with the traditional fine-tuning scheme in an energy-efficient way. © 2015 I

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Towards Depth-continuous Scene Representation with Displacement Field for Robust Light Field Depth Estimation

引用

IEEE Transactions on Multimedia 2025年

作者： Chen, Rongshan Sheng, Hao Yang, Da Cong, Ruixuan Cui, Zhenglong Wang, Sizhe Wang, Tun Zhao, Mingyuan Beihang University State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beijing100191 China Beihang University Key Laboratory of Data Science and Intelligent Computing International Innovation Institute 166 Shuanghongqiao Street Pingyao Town Yuhang District Hangzhou31 1115 China Macao Polytechnic University Faculty of Applied Sciences Macao999078 China

The light field (LF) captures both the spatial and angular information of scenes, enabling accurate depth estimation. However, previous deep learning methods typically model surface depth only while ignoring the continuous nature of depth in 3D scenes. In this paper, we use the displacement field (DF) to describe this continuous property, and propose a novel depth-continuous scene representation for robust LF depth estimation. Experiments demonstrate that our representation enables the network to generate highly detailed depth maps with fewer parameters and faster speeds. Specifically, inspired by the signed distance field in 3D object descriptions, we aim to exploit the intrinsic depth-continuous property of 3D scenes via DF and define a novel depth-continuous scene representation. Then, we introduce a simple, yet general, learning framework for depth-continuous scene embedding, and the proposed network, DepthDF, achieves state-of-the-art performance on both synthetic and real-world LF datasets, ranking 1st on the HCI 4D light field benchmark. Furthermore, previous LF depth estimation methods can also be seamlessly integrated into this framework. Finally, we extend this framework beyond LF depth estimation to various tasks, including multiview stereo depth inference, LF superresolution, and LF salient object detection. Our experiments demonstrate an improved performance when continuous scene representation is applied, suggesting that our framework can potentially provide insights for more fields. © 1999-2012 IEEE.

关键词： Stereo image processing

来源：评论

学校读者我要写书评

暂无评论

Privacy-Aware Joint DNN Model Deployment and Partition Optimization for Delay-Efficient Collaborative Edge Inference

arXiv

引用

arXiv 2025年

作者： Cheng, Zhipeng Xia, Xiaoyu Wang, Hong Liwang, Minghui Chen, Ning Fan, Xuwei Wang, Xianbin School of Future Science and Engineering Soochow University Suzhou215006 China School of Computing Technologies RMIT University MelbourneVIC Australia Department of Control Science and Engineering The National Key Laboratory of Autonomous Intelligent Unmanned Systems Tongji University Shanghai201804 China Frontiers Science Center for Intelligent Autonomous Systems Ministry of Education Tongji University Shanghai201804 China Qingdao China College of Computer and Information Sciences Fujian Agriculture and Forestry University Fuzhou350002 China Department of Electrical and Computer Engineering Western University ON Canada

Edge inference (EI) is a key solution to address the growing challenges of delayed response times, limited scalability, and privacy concerns in cloud-based Deep Neural Network (DNN) inference. However, deploying DNN models on resource-constrained edge devices faces more severe challenges, such as model storage limitations, dynamic service requests, and privacy risks. This paper proposes a novel framework for privacy-aware joint DNN model deployment and partition optimization to minimize long-term average inference delay under resource and privacy constraints. Specifically, the problem is formulated as a complex optimization problem considering model deployment, user-server association, and model partition strategies. To handle the NP-hardness and future uncertainties, a Lyapunov-based approach is introduced to transform the long-term optimization into a single-time-slot problem, ensuring system performance. Additionally, a coalition formation game model is proposed for edge server association, and a greedy-based algorithm is developed for model deployment within each coalition to efficiently solve the problem. Extensive simulations show that the proposed algorithms effectively reduce inference delay while satisfying privacy constraints, outperforming baseline approaches in various scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Exploring Communication-efficient Federated Learning via Stateless In-network Aggregation

引用

IEEE Transactions on Mobile Computing 2025年

作者： Xia, Junxu Cheng, Geyao Wu, Wenfei Luo, Lailong Guo, Deke National University of Defense Technology National Key Laboratory of Information Systems Engineering Changsha Hunan410073 China National University of Defense Technology State Key Laboratory of Complex & Critical Software Environment College of Information and Communication Changsha Hunan410073 China Peking University School of Computer Science Beijing100091 China

As an ambitious training paradigm, federated learning has garnered increasing attention in recent years, which enables collaborative training of a global model without accessing users' private data. However, due to the simultaneous and constant model updates gathering from massive distributed clients, the central server generally becomes a performance bottleneck. Additionally, the stateful aggregation (retaining all the updates from each client) conducted by the central server further poses potential threats to privacy, since it may recover the raw data based on such model updates inversely. The state-of-the-art methodologies, however, fail to address these two problems concurrently and efficiently. To this end, we propose GAIN, a secure aggregation acceleration service for federated learning. At its core, GAIN leverages programmable switches deployed at the edge network to aggregate model updates in a stateless manner before transmitting them to the central server. Consequently, GAIN can accelerate the transmission and aggregation of model updates while eliminating the chance of recovering private data. We evaluate the performance of GAIN through FPGA-based experiments and large-scale simulations. The results show that GAIN can effectively reduce bandwidth overhead and achieve up to 4.11× training throughput acceleration while prioritizing privacy protection. © 2025 IEEE.

关键词： Differential privacy

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：