检索结果-内蒙古大学图书馆

Hybrid two-level protection system for preserving pre-trained DNN models ownership

Neural Computing and Applications 2024年第34期36卷 21415-21449页

作者： Fkirin, Alaa Moursi, Ahmed Samy Attiya, Gamal El-Sayed, Ayman Shouman, Marwa A. Department of Electrical Engineering Faculty of Engineering Fayoum University Fayoum Egypt Computer Science and Engineering Department Faculty of Electronic Engineering Menoufia Governorate Menouf32952 Egypt

Recent advancements in deep neural networks (DNNs) have made them indispensable for numerous commercial applications. These include healthcare systems and self-driving cars. Training DNN models typically demands substantial time, vast datasets and high computational costs. However, these valuable models face significant risks. Attackers can steal and sell pre-trained DNN models for profit. Unauthorised sharing of these models poses a serious threat. Once sold, they can be easily copied and redistributed. Therefore, a well-built pre-trained DNN model is a valuable asset that requires protection. This paper introduces a robust hybrid two-level protection system for safeguarding the ownership of pre-trained DNN models. The first-level employs zero-bit watermarking. The second-level incorporates an adversarial attack as a watermark by using a perturbation technique to embed the watermark. The robustness of the proposed system is evaluated against seven types of attacks. These are Fast Gradient Method Attack, Auto Projected Gradient Descent Attack, Auto Conjugate Gradient Attack, Basic Iterative Method Attack, Momentum Iterative Method Attack, Square Attack and Auto Attack. The proposed two-level protection system withstands all seven attack types. It maintains accuracy and surpasses current state-of-the-art methods. © The Author(s) 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Full-model-free Adaptive Graph Deep Deterministic Policy Gradient Model for Multi-terminal Soft Open Point Voltage Control in Distribution Systems

引用

Journal of Modern Power Systems and Clean Energy 2024年第6期12卷 1893-1904页

作者： Huayi Wu Zhao Xu Minghao Wang Youwei Jia Department of Electrical and Electronic Engineering The Hong Kong Polytechnic UniversityHong KongChina Shenzhen Research Institute The Hong Kong Polytechnic UniversityShenzhenChina Department of Electrical and Computer Engineering University of MacaoMacaoChina Department of Electrical and Electronic Engineering Southern University of Science and TechnologyShenzhenChina

High penetration of renewable energy sources(RESs)induces sharply-fluctuating feeder power,leading to volt-age deviation in active distribution *** prevent voltage violations,multi-terminal soft open points(M-sOPs)have been integrated into the distribution systems to enhance voltage con-trol ***,the M-SOP voltage control recalculated in real time cannot adapt to the rapid fluctuations of photovol-taic(PV)power,fundamentally limiting the voltage controllabili-ty of *** address this issue,a full-model-free adaptive graph deep deterministic policy gradient(FAG-DDPG)model is proposed for M-SOP voltage ***,the attention-based adaptive graph convolutional network(AGCN)is lever-aged to extract the complex correlation features of nodal infor-mation to improve the policy learning ***,the AGCN-based surrogate model is trained to replace the power flow cal-culation to achieve model-free ***,the deep deterministic policy gradient(DDPG)algorithm allows FAG-DDPG model to learn an optimal control strategy of M-SOP by continuous interactions with the AGCN-based surrogate *** tests have been performed on modified IEEE 33-node,123-node,and a real 76-node distribution systems,which demonstrate the effectiveness and generalization ability of the proposed FAG-DDPGmodel.

关键词： Soft open point graph attention graph convolutional network reinforcement learning voltage control distribution system deep deterministic policy gradient

来源：评论

学校读者我要写书评

暂无评论

Ant lion optimization based inertia weight optimized KGMO for mobility Management in Heterogeneous LTE cellular networks

引用

Multimedia Tools and Applications 2025年第17期84卷 17907-17928页

作者： Venkata Narasimha Reddy, G. Jayudu, T Venkata Naga Komarolu, Janardhan Rajesh, Nichenametla Reddy, B Lakshmi Narayana Department of Computer Science and Engineering St. Johns College of Engineering and Technology Yerrakota Yemmiganur India Anantapur India Nandyal India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Department of Computer Science and Engineering SV College of Engineering Kadapa India

This study proposes a hybrid optimization-based mobility management strategy employing Kinetic Gas Molecular Optimization (KGMO) and Ant Lion Optimization (ALO). Initially, KGMO calculates particle properties, such as gas molecule position and velocity, based on kinetic energy principles. While KGMO demonstrates expedited convergence in large-dimensional spaces, its limitations prompt the hybridization with ALO. ALO modifies the inertia weight of KGMO to mitigate these issues. The proposed KGMO-ALO approach is implemented and validated in a MATLAB environment, compared against other meta-heuristic techniques like Seagull and Monarch Butterfly Optimizations across various performance metrics including throughput, bit error rate, end-to-end delay, and HO. Existing techniques such as PSO, MBO, and SOA exhibit superior performance primarily in scenarios with high user counts. The underperformance of ALO is attributed to its reliance on the best antlion solution in each optimization round. By leveraging the hybrid KGMO-ALO approach, this study aims to overcome these limitations and advance mobility management strategies in heterogeneous LTE cellular networks. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Heterogeneous networks

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

Time Parameter Based Low-Energy Data Encryption Method for Mobile Applications

引用

computer Modeling in engineering & sciences 2024年第9期140卷 2779-2794页

作者： Li-Woei Chen Kun-Lin Tsai Fang-Yie Leu Wen-Cheng Jiang Shih-Ting Tseng Department of Computer and Information Sciences Chinese Military AcademyKaohsiung830TaiwanChina Department of Electrical Engineering Tunghai UniversityTaichung407TaiwanChina Department of Computer Science Tunghai UniversityTaichung407TaiwanChina

Various mobile devices and applications are now used in daily *** devices require high-speed data processing,low energy consumption,low communication latency,and secure data transmission,especially in 5G and 6G mobile ***-security cryptography guarantees that essential data can be transmitted securely;however,it increases energy consumption and reduces data processing ***,this study proposes a low-energy data encryption(LEDE)algorithm based on the Advanced Encryption Standard(AES)for improving data transmission security and reducing the energy consumption of encryption in Internet-of-Things(IoT)*** the proposed LEDE algorithm,the system time parameter is employed to create a dynamic S-Box to replace the static S-Box of *** indicated that six-round LEDE encryption achieves the same security level as 10-round conventional AES *** reduction in encryption time results in the LEDE algorithm having a 67.4%lower energy consumption and 43.9%shorter encryption time than conventional AES;thus,the proposed LEDE algorithm can improve the performance and the energy consumption of IoT edge devices.

关键词： Mobile application security AES data encryption time parameter mobile device

来源：评论

学校读者我要写书评

暂无评论

An ensemble based approach for violence detection in videos using deep transfer learning

引用

Multimedia Tools and Applications 2025年第12期84卷 11001-11025页

作者： Kaur, Gurmeet Singh, Sarbjeet Department of Computer Science and Engineering UIET Panjab University Chandigarh India

The detection of violence in videos has become an extremely valuable application in real-life situations, which aim to maintain and protect people’s safety. Despite the complexities inherent in videos and the abrupt nature of violent actions, the field has seen several approaches, yet achieving consistent performance remains elusive, especially with advanced real-life datasets. Presenting a solution, the paper proposes a Bagging ensemble based approach comprising three pretrained models integrated with stacked Long Short-Term Memory (LSTM) to enhance individual model performance. This ensemble approach is rigorously analyzed on two publicly accessible datasets, RLVS and RWF-2000, providing remarkable accuracy (96.6%, 92.7%) and F1-scores (96.6%, 93.0%). Additionally, a cross-dataset analysis demonstrates the model’s ability to generalize across diverse datasets. Furthermore, a study of ablation highlighting the efficacy and optimal selection of components in augmenting the proposed ensemble’s efficiency. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Deep learning approaches to address cold start and long tail challenges in recommendation systems: a systematic review

引用

Multimedia Tools and Applications 2025年第5期84卷 2293-2325页

作者： Jangid, Manisha Kumar, Rakesh Department of Computer Science & Engineering Central University of Haryana Haryana India

Recommendation systems (RS) have become prevalent across different domains including music, e-commerce, e-learning, entertainment, and social media to address the issue of information overload. While traditional RS approaches have achieved significant success in delivering recommendations, they still face issues including sparse data, diversity, cold start, and long tail problem. The emergence of deep learning as a prominent and extensively studied topic has shown significant potential in addressing these challenges in RS. Deep learning captures intricate patterns of interaction and precisely reflects user preferences, allowing for encoding complex abstractions in data representation and enhancing information processing capabilities. This paper provides an extensive survey of the existing literature on recommendation systems. We will begin by providing a foundational understanding of the core concepts and terminology of recommendation systems and significance of deep learning. Secondly, we talk about the original studies being conducted on deep learning methods and solutions to address "Cold start and long tail" challenges in recommendation. Thirdly, we examine the potential future directions of research pertaining to deep learning-based recommender systems (DLRS). Our review provides valuable insights for both researchers and practitioners in using deep learning to address challenges in recommendation and in developing effective and efficient recommendation systems. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Novel Tensor Decomposition-Based Efficient Detector for Low-Altitude Aerial Objects With Knowledge Distillation Scheme

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 487-501页

作者： Nianyin Zeng Xinyu Li Peishu Wu Han Li Xin Luo Department of Instrumental and Electrical Engineering Xiamen UniversityXiamen 361005China IEEE College of Computer and Information Science Southwest UniversityChongqing 400715China

Unmanned aerial vehicles(UAVs) have gained significant attention in practical applications, especially the low-altitude aerial(LAA) object detection imposes stringent requirements on recognition accuracy and computational resources. In this paper, the LAA images-oriented tensor decomposition and knowledge distillation-based network(TDKD-Net) is proposed,where the TT-format TD(tensor decomposition) and equalweighted response-based KD(knowledge distillation) methods are designed to minimize redundant parameters while ensuring comparable performance. Moreover, some robust network structures are developed, including the small object detection head and the dual-domain attention mechanism, which enable the model to leverage the learned knowledge from small-scale targets and selectively focus on salient features. Considering the imbalance of bounding box regression samples and the inaccuracy of regression geometric factors, the focal and efficient IoU(intersection of union) loss with optimal transport assignment(F-EIoU-OTA)mechanism is proposed to improve the detection accuracy. The proposed TDKD-Net is comprehensively evaluated through extensive experiments, and the results have demonstrated the effectiveness and superiority of the developed methods in comparison to other advanced detection algorithms, which also present high generalization and strong robustness. As a resource-efficient precise network, the complex detection of small and occluded LAA objects is also well addressed by TDKD-Net, which provides useful insights on handling imbalanced issues and realizing domain adaptation.

关键词： Attention mechanism knowledge distillation(KD) object detection tensor decomposition(TD) unmanned aerial vehicles(UAVs)

来源：评论

学校读者我要写书评

暂无评论

Low-light image enhancement using the illumination boost algorithm along with the SKWGIF method

引用

Multimedia Tools and Applications 2025年第17期84卷 18651-18685页

作者： Radmand, Elnaz Saberi, Erfan Sorkhi, Ali Ghanbari Pirgazi, Jamshid Department of Computer Engineering University of Science and Technology of Mazandaran Behshahr Iran

Low-light image enhancement is highly desirable for outdoor image processing and computer vision applications. Research conducted in recent years has shown that images taken in low-light conditions often pose two main problems, the first of which is low visibility (i.e., small pixel intensities). Secondly, due to the low signal-to-noise ratio, noise also becomes prominent and obscures the image content. For this reason, images with low noise are usually employed in this application, a practice not possible in the real world. In this regard, a hybrid method is proposed which is based on the illumination boost algorithm (IBA) and weighted guided image filtering with steering kernel (SKWGIF). IBA is used to raise the values of low and medium intensity pixels while preventing excessive increases in high-value pixels. SKWGIF is employed to denoise and augment image details by adjusting its parameters based on the output of the previous step. The proposed method utilizes the LOL v1, LOL v2 and ExDark datasets Our hybrid method’s comprehensive approach to low-light image enhancement produced better outcomes than previous methods. Quantitative results have shown that the proposed model outperforms state-of-the-art (SOTA) models on the LOL v1 dataset, achieving a PSNR value of 18.80. Through the successful resolution of visibility and noise reduction issues, our approach led to notable gains in image quality measures, including SSIM, PSNR, BRISQUE, and NIQE. IBA’s ability to selectively boost intensity improved image visibility without producing overexposure artifacts, and SKWGIF effectively reduced noise while enhancing image details. The combined effect produced improved image quality that was superior to that of single techniques or already-used hybrid approaches. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep learning approaches and biomarkers in medical diagnosis

引用

Recent Patents on engineering 2024年第3期18卷 13-26页

作者： Malik, Pardeep Singh, Sukhdip Computer Science and Engineering Department DCRUST Haryana Sonipat India

The size of the medical information system is growing gradually. Due to this, traditional data analysis for extracting helpful information for any disease has become inefficient in providing accurate real-time valid information. Traditional data mining and statistical learning techniques, which lack sufficient domain knowledge on a complicatedly colossal amount of data, need to stop adopting new advances in deep learning technologies. Thus, the use of sophisticated machines with in-depth understanding and analysis capability is vital to provide real-time information in detecting and diagnosing diseases in the healthcare system. In this paper, we study recent deep learning approaches which are capable of working on high-dimensional and multi-dimensional data. These approaches have been deployed to identify the root cause of various diseases like Cancer, Lung Diseases, Heart Diseases, Diabetes, Hepatitis, Alzheimer’s, Dengue, Parkinson’s, etc. In this study, our key contributions are: 1. A decent overview of the deep learning techniques. 2. Several modalities in the diagnosis of various diseases. 3. Set out recent trends in various applications of deep learning in healthcare, some of which are analysis and diagnosis of medical images, precision medicine, drug discovery, predictive analysis to support clinical decisions, and sustainable public health. 4. Several deep learning approaches with their performance are described in detail. 5. Although deep learning has achieved notable performance in detecting AD, there are several limitations, especially the availability of the patient’s data for training deep learning models on a particular disease is comparatively much less than required. © 2024 Bentham science Publishers.

关键词： Diagnosis

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：