检索结果-内蒙古大学图书馆

Deep domain adaptation by joint distribution neural matching

Neural Computing and Applications 2025年第19期37卷 14541-14561页

作者： Hong, Zijie Chen, Sentao Wen, Lisheng Yang, Xiaowei School of Software Engineering South China University of Technology Panyu District Guangdong Guangzhou510006 China Department of Computer Science Shantou University Daxue Road Guangdong Shantou515063 China

Domain adaptation aims to learn a prediction model that performs well in a target domain with unlabeled data by harnessing the distributionally different labeled data from a source domain. In this paper, we design a simple yet powerful neural network approach named joint distribution neural matching (JOINT) to address the challenge of joint distribution difference/mismatch in domain adaptation. Our JOINT approach matches the source joint distribution and the target one in the activation space of a neural network by minimizing an estimate of the Jensen–Shannon (JS) divergence between the two joint distributions. The estimated JS divergence is derived in an explicit form, which frees our approach from solving a minimax adversarial problem when matching the distributions. Experiments on four representative large-scale visual recognition datasets show that our JOINT approach outperforms the state-of-the-art under both unsupervised and semi-supervised domain adaptation settings. Our code will be available at https://***/TitanRisen/JOINT-CODE. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards Cache-Assisted Hierarchical Detection for Real-Time Health Data Monitoring in IoHT

引用

computers, Materials & Continua 2023年第11期77卷 2529-2544页

作者： Muhammad Tahir Mingchu Li Irfan Khan Salman AAl Qahtani Rubia Fatima Javed Ali Khan Muhammad Shahid Anwar School of Software Technology Dalian University of Technology(DUT)Dalian116621China School of Software Technology Key Laboratory for Ubiquitous Network and Service Software of Liaoning ProvinceDalian116650China Department of Computer Engineering King Saud UniversityRiyadh11543Saudi Arabia School of Software Tsinghua UniversityBeijing100084China Department of Software Engineering University of Science and TechnologyBanu28100Pakistan Department of AI and Software Gachon UniversitySeongnamsi13120Korea

Real-time health data monitoring is pivotal for bolstering road services’safety,intelligence,and efficiency within the Internet of Health Things(IoHT)***,delays in data retrieval can markedly hinder the efficacy of big data awareness detection *** advocate for a collaborative caching approach involving edge devices and cloud networks to combat *** strategy is devised to streamline the data retrieval path,subsequently diminishing network *** an adept cache processing scheme poses its own set of challenges,especially given the transient nature of monitoring data and the imperative for swift data transmission,intertwined with resource allocation *** paper unveils a novel mobile healthcare solution that harnesses the power of our collaborative caching approach,facilitating nuanced health monitoring via edge *** system capitalizes on cloud computing for intricate health data analytics,especially in pinpointing health *** the dynamic locational shifts and possible connection disruptions,we have architected a hierarchical detection system,particularly during *** system caches data efficiently and incorporates a detection utility to assess data freshness and potential lag in response ***,we introduce the Cache-Assisted Real-Time Detection(CARD)model,crafted to optimize *** the inherent complexity of the NP-hard CARD model,we have championed a greedy algorithm as a *** reveal that our collaborative caching technique markedly elevates the Cache Hit Ratio(CHR)and data freshness,outshining its contemporaneous benchmark *** empirical results underscore the strength and efficiency of our innovative IoHT-based health monitoring *** encapsulate,this paper tackles the nuances of real-time health data monitoring in the IoHT landscape,presenting a joint edge-cloud caching strategy paired with a hierarchical detection *** methodology yields enh

关键词： Real-time health data monitoring Cache-Assisted Real-Time Detection(CARD) edge-cloud collaborative caching scheme hierarchical detection Internet of Health Things(IoHT)

来源：评论

学校读者我要写书评

暂无评论

Combatting the TrickBot Threat: Analysis, Impact, and Defensive Strategies in Cybersecurity 17

Combatting the TrickBot Threat: Analysis, Impact, and Defens...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Cao, Jintao Null, Allie Stewart, Marissa Bhunia, Suman Salman, Mohammad Miami University Department of Computer Science and Software Engineering OxfordOH United States University of Anbar College of Computer Anbar Iraq

ISBN: (纸本)9798350351637

The TrickBot Botnet, emerging in late 2016, has been a significant cybersecurity threat, leveraging sophisticated attack vectors such as phishing emails, network vulnerabilities, and secondary payloads. This paper provides a comprehensive analysis of TrickBot's evolution, attack methodologies, and widespread impact on individual users, businesses, and government entities. Despite some disruptions to its infrastructure, TrickBot has demonstrated remarkable resilience, continually adapting its tactics to evade detection and enhance its malicious capabilities. Our research offers detailed insights into the operational mechanisms of TrickBot, supported by extensive data on its propagation and impact. Furthermore, we evaluate various defense strategies, including advanced technical measures and human-centric approaches, to mitigate the ongoing threat posed by TrickBot and similar botnets. The findings underscore the critical need for continuous vigilance and innovation in cybersecurity practices to effectively counter such persistent threats. © 2024 IEEE.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

A Curious Case of Searching for the Correlation between Training Data and Adversarial Robustness of Transformer Textual Models 62

A Curious Case of Searching for the Correlation between Trai...

引用

Findings of the 62nd Annual Meeting of the Association for Computational Linguistics, ACL 2024

作者： Dang, Cuong Le, Dung D. Le, Thai FPT Software AI Center Viet Nam College of Engineering and Computer Science VinUniversity Viet Nam Department of Computer Science Indiana University United States

ISBN: (纸本)9798891760998

Existing works have shown that fine-tuned textual transformer models achieve state-of-the-art prediction performances but are also vulnerable to adversarial text perturbations. Traditional adversarial evaluation is often done only after fine-tuning the models and ignoring the training data. In this paper, we want to prove that there is also a strong correlation between training data and model robustness. To this end, we extract 13 different features representing a wide range of input fine-tuning corpora properties and use them to predict the adversarial robustness of the fine-tuned models. Focusing mostly on encoder-only transformer models BERT and RoBERTa with additional results for BART, ELECTRA, and GPT2, we provide diverse evidence to support our argument. First, empirical analyses show that (a) extracted features can be used with a lightweight classifier such as Random Forest to predict the attack success rate effectively, and (b) features with the most influence on the model robustness have a clear correlation with the robustness. Second, our framework can be used as a fast and effective additional tool for robustness evaluation since it (a) saves 30x-193x runtime compared to the traditional technique, (b) is transferable across models, (c) can be used under adversarial training, and (d) robust to statistical randomness. Our code is publicly available at https://***/CaptainCuong/RobustText_ACL2024. © 2024 Association for Computational Linguistics.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Federated transfer learning for distributed drought stage prediction

引用

Discover Artificial Intelligence 2025年第1期5卷 1-13页

作者： Raza, Muhammad Owais Umar, Aqsa Rasheed, Jawad Asuroglu, Tunc Alsubai, Shtwai Department of Computer Engineering Istanbul Sabahattin Zaim University Istanbul34303 Turkey Department of Computer Science Sindh Madressatul Islam University Karachi74000 Pakistan Department of Software Engineering Istanbul Nisantasi University Istanbul34398 Turkey Applied Science Research Center Applied Science Private University Amman Jordan Faculty of Medicine and Health Technology Tampere University Tampere33720 Finland VTT Technical Research Centre of Finland Tampere33720 Finland Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Al-Kharj11942 Saudi Arabia

Due to the uncertain nature of drought, it is one of the most menacing natural disasters. Drought modeling (Prediction, Detection, Forecasting, and Stage Prediction) is very essential for efficient policy making. But one of the key problems with drought modeling is the limited availability of centralized datasets. To address this problem, we are a novel proposing federated learning based transfer learning models for the prediction of drought stages. In this study, satellite image dataset was collected from the Tharparkar district (prone to drought) of Pakistan. We trained the dataset using traditional and federated learning approaches, comparing centralized ML models, pre-trained models, and their respective federated learning models (FL-ResNet, FL-DenseNet, FL-MobileNet). The development of these models is the novel aspect of the study specifically for the use case of drought stage prediction. Based on the final evaluation, FL-MobileNet achieved 82% precision while baseline MobileNet scored 68%. The results show the effectiveness of novelty (federated learning), that our proposed framework improves the performance of the drought stage classification task. © The Author(s) 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Reference Trustable Decoding: A Training-Free Augmentation Paradigm for Large Language Models 38

Reference Trustable Decoding: A Training-Free Augmentation P...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Shi, Luohe Yao, Yao Li, Zuchao Zhang, Lefei Zhao, Hai National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Department of Computer Science and Engineering Shanghai Jiao Tong University China

Large language models (LLMs) have rapidly advanced and demonstrated impressive capabilities. In-Context Learning (ICL) and Parameter-Efficient Fine-Tuning (PEFT) are currently two mainstream methods for augmenting LLMs to downstream tasks. ICL typically constructs a few-shot learning scenario, either manually or by setting up a Retrieval-Augmented Generation (RAG) system, helping models quickly grasp domain knowledge or question-answering patterns without changing model parameters. However, this approach involves trade-offs, such as slower inference speed and increased space occupancy. PEFT assists the model in adapting to tasks through minimal parameter modifications, but the training process still demands high hardware requirements, even with a small number of parameters involved. To address these challenges, we propose Reference Trustable Decoding (RTD), a paradigm that allows models to quickly adapt to new tasks without fine-tuning, maintaining low inference costs. RTD constructs a reference datastore from the provided training examples and optimizes the LLM's final vocabulary distribution by flexibly selecting suitable references based on the input, resulting in more trustable responses and enabling the model to adapt to downstream tasks at a low cost. Experimental evaluations on various LLMs using different benchmarks demonstrate that RTD establishes a new paradigm for augmenting models to downstream tasks. Furthermore, our method exhibits strong orthogonality with traditional methods, allowing for concurrent usage. Our code can be found at https://***/ShiLuohe/ReferenceTrustableDecoding. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analyzing the Impact of Preprocessing Techniques on the Efficiency and Accuracy of Sentiment Classification Algorithms 15

Analyzing the Impact of Preprocessing Techniques on the Effi...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Nikhila Kanigiri, Sai Mekuriyaw, Chachi Goodman, Garrett Alexiou, Michail S. Kennesaw State University Department of Computer Science MariettaGA United States Miami University Computer Science and Software Engineering OxfordOH United States

ISBN: (纸本)9798350368833

In the era of data-driven decision-making, the ability to rapidly and accurately analyze vast amounts of textual data is essential. This paper examines the role of text pre-processing techniques in enhancing the effectiveness of sentiment classification algorithms. Such algorithms are pivotal in interpreting the emotional tone of texts and serving as a preliminary step towards reverse-engineering complex data systems. Through comprehensive analysis, we assess the impact of various preprocessing strategies such as keyword removal, lemmatization, and stemming and their combination on the performance of both traditional and advanced machine learning models, including Random Forest, Support Vector Machine (SVM), Extreme Gradient Boosting (XGBoost), and Bidirectional Encoder Representations from Transformers (BERT). The current study evaluates the balance between efficiency and accuracy in sentiment analysis algorithms, illustrating the impact of preprocessing techniques. In addition, it aims to serve as a guideline for selecting preprocessing methods that optimize model performance in both sentiment analysis and textual data reverse-engineering. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

DAPoinTr: Domain Adaptive Point Transformer for Point Cloud Completion 39

DAPoinTr: Domain Adaptive Point Transformer for Point Cloud ...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Li, Yinghui Zhou, Qianyu Gong, Jingyu Zhu, Ye Dazeley, Richard Zhao, Xinkui Lu, Xuequan School of Information Technology Deakin University Australia Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Technology East China Normal University Shanghai China School of Software Technology Zhejiang University Ningbo China Department of Computer Science and Software Engineering The University of Western Australia Australia

ISBN: (纸本)157735897X

Point Transformers (PoinTr) have shown great potential in point cloud completion recently. Nevertheless, effective domain adaptation that improves transferability toward target domains remains unexplored. In this paper, we delve into this topic and empirically discover that direct feature alignment on point Transformer’s CNN backbone only brings limited improvements since it cannot guarantee sequence-wise domain-invariant features in the Transformer. To this end, we propose a pioneering Domain Adaptive Point Transformer (DAPoinTr) framework for point cloud completion. DAPoinTr consists of three key components: Domain Query-based Feature Alignment (DQFA), Point Token-wise Feature alignment (PTFA), and Voted Prediction Consistency (VPC). In particular, DQFA is presented to narrow the global domain gaps from the sequence via the presented domain proxy and domain query at the Transformer encoder and decoder, respectively. PTFA is proposed to close the local domain shifts by aligning the tokens, i.e., point proxy and dynamic query, at the Transformer encoder and decoder, respectively. VPC is designed to consider different Transformer decoders as multiple of experts (MoE) for ensembled prediction voting and pseudo-label generation. Extensive experiments with visualization on several domain adaptation benchmarks demonstrate the effectiveness and superiority of our DAPoinTr compared with state-of-the-art methods. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Synergistic Integration of Blockchain and software-Defined Networking in the Internet of Energy Systems 6

Synergistic Integration of Blockchain and Software-Defined N...

引用

6th International Conference on Blockchain Computing and Applications, BCCA 2024

作者： Hayyolalam, Vahideh Zekiye, Abdulrezzak Abuzahra, Hamza Özkasap, Öznur Karakus, Murat Guler, Evrim Uludag, Suleyman Department of Computer Engineering Koç University İstanbul Turkey Department of Software Engineering Ankara University Ankara Turkey Department of Computer Engineering Bartin University Bartin Turkey Department of Computer Science University of Michigan FlintMI United States

ISBN: (纸本)9798350351538

Peer-to-peer (P2P) energy trading, Smart Grids (SG), and electric vehicle energy management are integral components of the Internet of Energy (IoE) field. The integration of software-Defined Networks (SDNs) and Blockchain (BC) technologies into the IoE domain offers potential benefits that have only been studied in the literature in a few works. In this paper, we investigate the state-of-art solutions that leverage both SDNs and blockchain within the realm of the IoE. We categorize these solutions based on the method of integrating SDN and BC into two categories. The first category is the blockchain for SDN, where blockchain enhances the SDN directly. The second category is blockchain and SDN, where both technologies are used to enhance the proposed solutions. We identify three distinct blockchain applications based on their usage: decentralizing the SDN control plane, serving as a decentralized platform, and improving security measures. Similarly, we observe that SDN serves as a performance enhancer, a substitute for traditional networking, and solely as a control and management framework. It is posited that integrating SDNs and blockchain into IoE leads to performance enhancements, improves security, enables decentralized operations, and eliminates single points of failure in the SDN control plane. Additionally, some unaddressed issues, such as energy efficiency, smart contract management, and scalability, are discussed as potential future directions. © 2024 IEEE.

关键词： Internet of Energy

来源：评论

学校读者我要写书评

暂无评论

A Novel Blockchain-Based Deepfake Detection Method Using Federated and Deep Learning Models

引用

Cognitive Computation 2024年第3期16卷 1073-1091页

作者： Heidari, Arash Navimipour, Nima Jafari Dag, Hasan Talebi, Samira Unal, Mehmet Department of Software Engineering Haliç University Istanbul34060 Turkey Department of Computer Engineering Kadir Has University Istanbul Turkey Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliou64002 Taiwan Department of Information Technology Kadir Has University Istanbul Turkey Department of Computer Science University of Texas at San Antonio San AntonioTX United States Department of Computer Engineering Nisantasi University Istanbul Turkey

In recent years, the proliferation of deep learning (DL) techniques has given rise to a significant challenge in the form of deepfake videos, posing a grave threat to the authenticity of media content. With the rapid advancement of DL technology, the creation of convincingly realistic deepfake videos has become increasingly prevalent, raising serious concerns about the potential misuse of such content. Deepfakes have the potential to undermine trust in visual media, with implications for fields as diverse as journalism, entertainment, and security. This study presents an innovative solution by harnessing blockchain-based federated learning (FL) to address this issue, focusing on preserving data source anonymity. The approach combines the strengths of SegCaps and convolutional neural network (CNN) methods for improved image feature extraction, followed by capsule network (CN) training to enhance generalization. A novel data normalization technique is introduced to tackle data heterogeneity stemming from diverse global data sources. Moreover, transfer learning (TL) and preprocessing methods are deployed to elevate DL performance. These efforts culminate in collaborative global model training zfacilitated by blockchain and FL while maintaining the utmost confidentiality of data sources. The effectiveness of our methodology is rigorously tested and validated through extensive experiments. These experiments reveal a substantial improvement in accuracy, with an impressive average increase of 6.6% compared to six benchmark models. Furthermore, our approach demonstrates a 5.1% enhancement in the area under the curve (AUC) metric, underscoring its ability to outperform existing detection methods. These results substantiate the effectiveness of our proposed solution in countering the proliferation of deepfake content. In conclusion, our innovative approach represents a promising avenue for advancing deepfake detection. By leveraging existing data resources and the power of FL

关键词： Blockchain

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：