检索结果-内蒙古大学图书馆

Privacy-Preserving Knowledge Distillation in Latency-Critical Federated Task Offloading for Consumer IoT Networks

IEEE Transactions on Consumer Electronics 2024年第1期71卷 239-251页

作者： Chen, Yishan Zhang, Jianwei Wang, Zhiqiang Dai, Wenshuo Gao, Honghao Deng, Shuiguang Jiangxi University of Science and Technology College of Information Engineering China Shanghai University School of Computer Engineering and Science China Gachon University College of Future Industry Korea Republic of Zhejiang University College of Computer Science and Technology China

Along with the explosive demand for massive data computation, federated local-edge-cloud computing enables many IoT task offloading processes and has recently gained widespread attention in consumer-centric healthcare. However, existing approaches for latency-critical task offloading do not pay sufficient attention to patient privacy data and thus are far from being ready for large-scale practical deployment. In this paper, a novel local-edge-cloud based federated learning framework with one-way knowledge distillation for latency-critical and security-aware task offloading is proposed, while a task offloading scheme based on deep reinforcement learning is presented. Then, based on the consideration of privacy guarantees, computing resources and offloading decisions, an optimization problem is formulated to minimize the overall latency of all tasks for local medical devices. Additionally, a pseudo-task mechanism is adopted in the federated framework for the uploaded weights to aggregate the models on the edges and the cloud. Besides, a one-way knowledge distillation mechanism is proposed to transfer knowledge from a teacher model to student models, which compresses the network parameters and reduces the model latency. Finally, experiments based on Chest X-Ray Images of Pneumonia are conducted for corroborating the theoretical results. © 1975-2011 IEEE.

关键词： Computation offloading

来源：评论

学校读者我要写书评

暂无评论

Design of a ML-based trust prediction model using intelligent TrustBoxes in challenged networks

引用

International Journal of Systems, Control and Communications 2024年第3期15卷 209-234页

作者： Barai, Smritikona Kundu, Anindita Bhaumik, Parama Department of Computer Science and Engineering Heritage Institute of Technology Kolkata India Department of Software Systems School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu India Department of Information Technology Jadavpur University Kolkata India

Challenged networks (CNs) contain resource-constrained nodes deployed in regions where human intervention is difficult. Opportunistic networks (OppNets) are CNs with no predefined source-to-destination paths. Due to their inherent properties, CNs and OppNets are highly susceptible to black-hole (BH) attacks, resulting in degraded packet-delivery ratio. In this work, an ML-based trust prediction model (MLTPM) is proposed to identify potential BH nodes in OppNets. MLTPM uses a novel function to calculate the total-trust-value (TTV) of each node. Intelligent TrustBoxes are introduced in the network to identify possible BH nodes, using TTV, along with five more node-behaviour features. TrustBoxes reduce the computational overhead of the resource-constrained nodes. Three simulated scenarios are compared - no detection, non-ML-based detection, and MLTPM, each using epidemic, prophet, and spray-and-wait routing protocols. MLTPM performs best with spray-and-wait, exhibiting about 25.21% and 80% mean improvement in delivery-ratio and dropped-message numbers respectively, compared to non-ML-based detection. An overall 12.62% improvement in delivery-ratio and 26.7% improvement in dropped messages is observed using MLTPM, compared to the above-mentioned scenarios. © 2024 Inderscience Enterprises Ltd.

关键词： HTTP

来源：评论

学校读者我要写书评

暂无评论

FLAG: frequency-based local and global network for face forgery detection

引用

Multimedia Tools and Applications 2025年第2期84卷 647-663页

作者： Zhou, Kai Sun, Guanglu Wang, Jun Wang, Jiahui Yu, Linsen School of Computer Science and Technology Harbin University of Science and Technology Harbin150080 China Department of Information Engineering and Mathematics University of Siena Siena53100 Italy

Deepfake detection aims to mitigate the threat of manipulated content by identifying and exposing forgeries. However, previous methods primarily tend to perform poorly when confronted with cross-dataset scenarios. To address the above issue, we propose an innovative hybrid network called the Frequency-based Local and Global (FLAG) network to explore local and global information with the help of frequency-domain cues for better generalization capability. In consideration of the fact that forged faces often exhibit flaws in the frequency domain, we design a Frequency-based Attention Enhancement Module (FAEM) to enhance the aggregation of CNN and Vision Transformer (ViT). In this design, local features from CNN are attentively enhanced by selected frequency coefficients in FAEM, facilitating generalizable global features learning by the ViT module. The effectiveness of the proposed method is validated via numerous experiments and the generalization performance is improved under cross-dataset scenarios. Especially, the proposed method have obtained an AUC of 99.26% and an ACC of 96.56% using intra-dataset experimental results on FaceForensics++ (C23). © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Automated GUI widgets classification

引用

Frontiers of computer science 2023年第1期17卷 233-235页

作者： Kabir Sulaiman SAID Liming NIE Yuanchang LIN Yaowen ZHENG Zuohua DING School of Computer Science and Technology Zhejiang Sci-Tech UniversityHangzhou 310018China School of Computer Science and Engineering Nanyang Technological UniversitySingap

1 Introduction Graphical User Interface(GUI)widgets classification entails classifying widgets into their appropriate domain-specific types(e.g.,CheckBox and EditText)[1,2].The widgets classification is essential as it supports several software engineering tasks,such as GUI design and testing[1,3].The ability to obtain better widget classification performance has become one of the keys to the success of these *** in recent years have proposed many techniques for improving widget classification performance[1,2,4].For example,Moran et al.[1]proposed a deep learning technique to classify GUI widgets into their domain-specific *** authors used the deep learning algorithm,a Convolutional Neural Network(CNN)architecture,to classify the GUI *** et al.[2]proposed combining text-based and non-text-based models to improve the overall performance of GUI widget detection while classifying the widgets with the ResNet50 model.

关键词： GUI User classify

来源：评论

学校读者我要写书评

暂无评论

Multi-strategy hybrid whale optimization algorithms for complex constrained optimization problems

引用

High technology Letters 2024年第1期30卷 99-108页

作者：王振宇 WANG Lei School of Computer Science and Engineering Xi'an University of TechnologyXi'an 710048P.R.China

A multi-strategy hybrid whale optimization algorithm(MSHWOA)for complex constrained optimization problems is proposed to overcome the drawbacks of easily trapping into local optimum,slow convergence speed and low optimization ***,the population is initialized by introducing the theory of good point set,which increases the randomness and diversity of the population and lays the foundation for the global optimization of the ***,a novel linearly update equation of convergence factor is designed to coordinate the abilities of exploration and *** the same time,the global exploration and local exploitation capabilities are improved through the siege mechanism of Harris Hawks optimization ***,the simulation experiments are conducted on the 6 benchmark functions and Wilcoxon rank sum test to evaluate the optimization performance of the improved *** experimental results show that the proposed algorithm has more significant improvement in optimization accuracy,convergence speed and robustness than the comparison algorithm.

关键词： whale optimization algorithm(WOA) good point set nonlinear convergence factor siege mechanism

来源：评论

学校读者我要写书评

暂无评论

Hybrid deep learning based digital image watermarking using GAN-LSTM and adaptive gannet optimization techniques

引用

Multimedia Tools and Applications 2024年 1-31页

作者： Shedole, Sambhaji Marutirao Santhi, V. School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Katpadi Vellore632014 India

Nowadays, multimedia technology is progressing everyday. It is very easy to duplicate, distribute and modify digital images with online editing software. Image security and privacy are critical aspects of the multimedia revolution. Therefore, digital image watermarking offers an alternative way out for image authentication. Currently, watermarking methods are crucial for safeguarding digital images. Several traditional watermarking approaches have been developed to protect images using spatial domains and transformations. Watermarking techniques that are more traditional are less resistant to repeated attacks. Deep learning-based watermarking has recently gained traction, greatly improving the safety of visual images in a variety of common applications. This study presents a robust and secure digital watermarking method for multimedia content protection and authentication. The watermark image is first transformed using the hybrid wavelet transform, and then it is encrypted using a chaos encryption algorithm. The cover image is simultaneously subjected to neighborhood-based feature extraction. Leveraging these extracted features, a novel Adaptive Gannet Optimization algorithm (AGOA) is employed to determine the optimal embedding location. Subsequently, the watermarked image is seamlessly integrated and extracted using the hybrid Generative adversarial network-based long short-term memory (GAN-LSTM) approach within the identified optimal region. Decryption and Inverse transformation are then used to get the original watermark image. Several previous methods, such as DNN, Deep-ANN, and Deep-CNN, are used to evaluate the performance of the proposed method. This technique improves multimedia content protection and authentication by guaranteeing strong and secure watermarking. The proposed method for digital image watermarking produced a peak signal-to-noise ratio of 46.412 and a mean square error of 24.512. Therefore, the proposed method performs well in digital image wa

关键词： Wavelet transforms

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Powered Authenticated Key Agreement Scheme With Reputation-Incentive Mechanism for Vehicle-to-Vehicle Communication in IoV

引用

IEEE Internet of Things Journal 2025年第13期12卷 25500-25515页

作者： Mukathe, Daniel Di, Wu Ahmed, Waheeb Worku, Tarik Dalian University of Technology School of Computer Science and Technology Dalian116024 China Tharaka University Department of Computer Science Marimanti193-60215 Kenya University of Aden Department of Computer Science and Engineering Aden009672 Yemen Injibara University Department of Computer Science Injibara6040 Ethiopia

The Internet of Vehicles (IoV) enhances road safety through real-time vehicle-to-vehicle (V2V) communication of traffic messages. However, V2V wireless connectivity poses security and privacy threats, as malicious adversaries can eavesdrop and modify V2V messages or compromise vehicle identity privacy. Existing authenticated key agreement (AKA) schemes attempt to address these threats but suffer from security flaws, computational inefficiency, high communication overhead, single points of failure, and trust deficits, making them unsuitable for resource-constrained and delay-sensitive IoV applications. To address the above challenges, we propose a blockchain-powered AKA scheme with a reputation-incentive mechanism (BAKARI) for V2V communication. BAKARI employs Schnorr signatures and lightweight elliptic curve cryptographic operations to improve computational efficiency, and minimizes communication overhead by completing the AKA phase with only two messages. BAKARI leverages blockchain ledger and smart contracts to maintain vehicle authentication information and V2V messages. Additionally, it incorporates a reputation-incentive model, where trustworthy vehicles are rewarded while malicious ones are penalized. A rigorous security analysis, including formal proof under the random or real model, informal analysis, and ProVerif verification, demonstrates BAKARI’s resilience against security and privacy threats. Performance evaluation shows that BAKARI balances computational efficiency, communication overhead, and security better than the benchmark schemes. Finally, simulations on Hyperledger Fabric and Veins frameworks validate BAKARI’s practicality in real-world IoV environments. © 2014 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

AttrLeaks on the Edge: Exploiting Information Leakage from Privacy-Preserving Co-inference

引用

Chinese Journal of Electronics 2023年第1期32卷 1-12页

作者： WANG Zhibo LIU Kaixin HU Jiahui REN Ju GUO Hengchang YUAN Wei School of Cyber Science and Engineering Wuhan University School of Cyber Science and Technology Zhejiang University Department of Computer Science and Technology Tsinghua University

Collaborative inference(co-inference) accelerates deep neural network inference via extracting representations at the device and making predictions at the edge server, which however might disclose the sensitive information about private attributes of users(e.g.,race). Although many privacy-preserving mechanisms on co-inference have been proposed to eliminate privacy concerns, privacy leakage of sensitive attributes might still happen during inference. In this paper, we explore privacy leakage against the privacy-preserving co-inference by decoding the uploaded representations into a vulnerable form. We propose a novel attack framework named AttrL eaks, which consists of the shadow model of feature extractor(FE), the susceptibility reconstruction decoder,and the private attribute classifier. Based on our observation that values in inner layers of FE(internal representation) are more sensitive to attack, the shadow model is proposed to simulate the FE of the victim in the blackbox scenario and generates the internal ***, the susceptibility reconstruction decoder is designed to transform the uploaded representations of the victim into the vulnerable form, which enables the malicious classifier to easily predict the private attributes. Extensive experimental results demonstrate that AttrLeaks outperforms the state of the art in terms of attack success rate.

关键词： Deep learning Privacy Collaboration Transforms Feature extraction Prediction algorithms Iron

来源：评论

学校读者我要写书评

暂无评论

Variance-SNR Based Noise Suppression on Linear Canonical Choi-Williams Distribution of LFM Signals

引用

Chinese Journal of Electronics 2022年第5期31卷 804-820页

作者： ZHANG Zhichao School of Mathematics and Statistics Nanjing University of Information Science and Technology School of Computer Science and Engineering Macau University of Science and Technology

By solving the existing expectation-signal-to-noise ratio(expectation-SNR) based inequality model of the closed-form instantaneous cross-correlation function type of Choi-Williams distribution(CICFCWD),the linear canonical transform(LCT) free parameters selection strategies obtained are usually *** the second-order moment variance outperforms the first-order moment expectation in accurately characterizing output SNRs, this paper uses the variance analysis technique to improve parameters selection strategies. The CICFCWD's average variance of deterministic signals embedded in additive zero-mean stationary circular Gaussian noise processes is first obtained. Then the so-called variance-SNRs are defined and applied to model a variance-SNR based inequality. A stronger inequalities system is also formulated by integrating expectation-SNR and variance-SNR based inequality models. Finally, a direct application of the system in noisy one-component and bi-component linear frequency-modulated(LFM) signals detection is studied. Analytical algebraic constraints on LCT free parameters newly derived seem more accurate than the existing ones, achieving better noise suppression effects. Our methods have potential applications in optical, radar, communication and medical signal processing.

关键词： linear canonical Choi-Williams distribution AWGN closed-form instantaneous cross-correlation function variance-SNR based inequality deterministic signals transforms LFM signal denoising statistical distributions Gaussian noise frequency modulation linear canonical transform free parameters signal detection average variance second-order moment variance expectation-signal-to-noise ratio variance-SNR based noise suppression CICFCWD analytical algebraic constraints LCT bicomponent linear frequency-modulated signals detection one-component linear frequency-modulated signals detection additive zero-mean stationary circular Gaussian noise processes LFM signals

来源：评论

学校读者我要写书评

暂无评论

Machine learning design of 400 MPa grade biodegradable Zn-Mn based alloys with appropriate corrosion rates

引用

International Journal of Minerals,Metallurgy and Materials 2024年第12期31卷 2727-2736页

作者： Wangzhang Chen Wei Gou Yageng Li Xiangmin Li Meng Li Jianxin Hou Xiaotong Zhang Zhangzhi Shi Luning Wang Beijing Advanced Innovation Center for Materials Genome Engineering State Key Laboratory for Advanced Metals and MaterialsSchool of Materials Science and EngineeringUniversity of Science and Technology BeijingBeijing 100083China Institute of Materials Intelligent Technology Liaoning Academy of MaterialsShenyang 110004China School of Computer and Communication Engineering Shunde Innovation SchoolUniversity of Science and Technology BeijingShunde 528399China

The commonly used trial-and-error method of biodegradable Zn alloys is costly and *** this study,based on the self-built database of biodegradable Zn alloys,two machine learning models are established by the first time to predict the ultimate tensile strength(UTS)and immersion corrosion rate(CR)of biodegradable Zn alloys.A real-time visualization interface has been established to design Zn-Mn based alloys;a representative alloy is *** tensile mechanical properties and immersion corrosion rate tests,its UTS reaches 420 MPa,and the prediction error is only 0.95%.CR is 73μm/a and the prediction error is 5.5%,which elevates 50 MPa grade of UTS and owns appropriate corrosion ***,influences of the selected features on UTS and CR are discussed in *** combined application of UTS and CR model provides a new strategy for synergistically regulating comprehens-ive properties of biodegradable Zn alloys.

关键词： Zn alloys machine learning alloy design performance prediction

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：