检索结果-内蒙古大学图书馆

TraCemop: Towards Federated Learning with Traceable Contribution Evaluation and Model Ownership Protection

IEEE Transactions on Mobile computing 2025年

作者： Liu, Jingwei Zhou, Zihan Sun, Rong Liu, Lei Lu, Rongxing Dustdar, Schahram Niyato, Dusit Ministry of Education Engineering Research Center of Blockchain Technology Application and Evaluation China Xidian University Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an710071 China Xidian University State Key Laboratory of Integrated Services Networks Xi'an710071 China Xidian University Guangzhou Institute of Technology Guangzhou510555 China Key Laboratory of Computing Power Network and Information Security Ministry of Education Jinan250014 China Queen's University School of Computing KingstonONK7L 2N8 Canada TU Wien Distributed Systems Group Austria UPF ICREA Barcelona Spain Nanyang Technological University School of Computer Science and Engineering Singapore

Federated Learning (FL) allows multiple clients to collaboratively train machine learning models without the need to share their local private data. As a result, it can effectively address the issue of data fragmentation. Nevertheless, insufficient evaluation of individual contributions and the lack of protections for both the intellectual property rights (IPR) of models and client privacy can greatly reduce clients' motivations in federated training. To address these challenges, this paper introduces the Traceable Contribution Evaluation and Model Ownership Protection (TraCemop) framework for federated learning, which allows each client to swiftly assess the contributions of others in each round, with integrated support for the traceability of evaluation results. To safeguard the intellectual property of models, a collective watermark is embedded in the global model. Additionally, a secure mechanism for verifying model ownership is also available in case of disputes. security analysis indicates that TraCemop is capable of resisting data reconstruction attacks as well as various types of model copyright infringements. Finally, we evaluate the proposed framework using two commonly-used datasets, and the experimental results show a significant improvement in the efficiency of contribution evaluation compared to existing methods. Meanwhile, IPR infringement tests on TraCemop reveal that the proposed framework is resilient against malicious efforts to monopolize model ownership. © 2002-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Robust Imagined Speech Production Using AI-Generated Content network for Patients with Language Impairments

引用

IEEE Transactions on Consumer Electronics 2024年

作者： Xu, Xu Fu, Chong Dalian University of Technology School of Software Dalian116621 China Northeastern University School of Computer Science and Engineering Shenyang110004 China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang110819 China Ministry of Education Engineering Research Center of Security Technology of Complex Network System Shenyang110004 China

Imagined speech production is critical for brain-computer interface systems. It is able to provide the communication ability for patients with language impairments. Nowadays, many studies have developed algorithms for this purpose. However, they often struggle with an issue that is the noise in physiological signals from various devices. This makes current methods have low robustness when performing speech generation. To this end, we propose a framework to robustly producing imagined speech for patients with language impairments. It is based on artificial intelligent-generated content (AIGC). In specific, this work develops a diffusion model to remove noise from brain signals, which are then converted and normalized into log-mel spectrograms. Next, the product feeds into a transformer-based model to extract local and global features. Finally, these enhanced features are inputted into full connected layers to generate the imagined speech. The effectiveness of our model is validated using the high-quality, i.e., single-word-production-Dutch-iBIDS dataset. It achieves Pearson correlation scores above 0.8 and standard deviations below 0.2 across different volunteers. Experimental results well demonstrate that our model is robust and has advantages over peer methods. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

PTGFI: A Prompt-Based Two-Stage Generative Framework for Function Name Inference

PTGFI: A Prompt-Based Two-Stage Generative Framework for Fun...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Menglu Wang Xiaohui Han Peipei Wang Wenbo Zuo Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

In the field of cybersecurity, analyzing malicious software or programs is crucial for preventing network attacks. Malicious code often exists in a stripped binary form to thwart analysis, presenting challenges for analysts. This study investigates inferring function names from stripped binary to aid security researchers in analyzing malicious code. We propose PTGFI, a Prompt-based Two-stage Generative framework for Function name Inference. The PTGFI framework transforms the task of inferring function names into a two-stage semantic generation problem. By capturing function descriptions of assembly functions and introducing prompt learning, effective inference of function names is achieved. In experiments, PTGFI outperforms the state-of-the-art model by 2.96 % in precision. Moreover, ablation studies demonstrate the effectiveness of advanced components within the PTGFI framework. We further validate the utility and reliability of function names generated by the PTGFI framework through case studies.

关键词： Analytical models Codes Accuracy Semantics Transforms Malware Reliability Computer crime Assembly Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Semantic-Aware Prompt Learning for Multimodal Sarcasm Detection

Semantic-Aware Prompt Learning for Multimodal Sarcasm Detect...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Guangjin Wang Bao Wang Fuyong Xu Zhenfang Zhu Peipei Wang Ru Wang Peiyu Liu School of Information Science and Engineering Shandong Normal University Jinan China School of Information Science and Electrical Engineering Shandong Jiao Tong University Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multimodal sarcasm detection aims to identify whether utterances express sarcastic intentions contrary to their literal meaning based on multimodal information. However, existing methods fail to explore the model’s "ability to understand" the semantics expressed by sentences in the image context from semantic diversity perspectives. In this paper, we propose a multi-view semantic awareness method, which concretizes semantics from multiple perspectives to improve the model’s ability to capture different semantic features. Specifically, two learnable prefixes are attached to the text representation respectively to construct semantic representations from both the literal meaning and sarcastic intention perspectives. Then, image-text information is further fused through cross-attention to guide the semantic representation of different perspectives in the image context. Finally, the semantics expressed by prefixes are strengthened through KL divergence, thereby encouraging the model to capture two distinctive semantic features. Experiments on benchmark datasets demonstrate the effectiveness of our method.

关键词： Semantics Benchmark testing Speech enhancement Signal processing Vectors Acoustics Context modeling

来源：评论

学校读者我要写书评

暂无评论

Joint Extraction of Entities and Relationships from Cyber Threat Intelligence based on Task-specific Fourier network

Joint Extraction of Entities and Relationships from Cyber Th...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Haiqing Lv Xiaohui Han Hui Cui Peipei Wang Wenbo Zuo Yang Zhou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

The increasing complexity of cyber threats and the emergence of new attack technologies have brought huge challenges to attack incident analysis and source tracing. Using cyber threat intelligence to build a Cyber security Knowledge Graph (CKG) provides a new technical solution for attack attribution. Constructing a CKG requires numerous entity and relationship triples extracted from unstructured cyber threat intelligence texts. However, existing entity and relationship joint extraction methods in cyber threat intelligence face two problems. Firstly, they share the same word embeddings for both subtasks, ignoring the fine-grained semantic differences between the subtasks. Secondly, they rarely consider the interaction between the features of the two subtasks, which is vital for capturing the semantic dependencies between the tasks. To address these issues, we propose a joint entity and relationship extraction model specifically designed for network security concepts. We utilize two lightweight Fourier networks with independent weights to build a feature extraction module for encoding fine-grained features for entity recognition and relationship extraction tasks. Furthermore, we use a subtask feature interaction strategy assisted by a gated attention mechanism to enhance feature interaction between entity recognition and relationship extraction tasks. Use fine-grained entity recognition task information to guide relationship extraction to capture semantic dependencies between tasks. Experimental results on a cyber threat intelligence dataset demonstrate that our model outperforms existing baselines.

关键词： Attention mechanisms Face recognition Semantics Neural networks Knowledge graphs Logic gates network security

来源：评论

学校读者我要写书评

暂无评论

Multi-Aspect Edge Device Association Based on Time-Series Dynamic Interaction networks

Multi-Aspect Edge Device Association Based on Time-Series Dy...

引用

IEEE Conference on Computer Communications Workshops, INFOCOM Wksps

作者： Xiaoteng Yang Jie Feng Xifei Song Feng Xu Yuan Liu Qingqi Pei Celimuge Wu School of Telecommunication Engineering Xidian University Xi'an China Shaanxi Key Laboratory of Blockchain and Secure Computing Xi'an China Cyberspace Institute of Advanced Technology of Guangzhou University Guangdong China Department of Computer and Network Engineering The University of Electro-Communications Tokyo Japan

ISBN: (数字)9798350384475

ISBN: (纸本)9798350384482

The exploration into the evolution of architectural structures in 6G edge computing nodes through time-series-based dynamic interactions offers a compelling investigation within complex systems. In the realm of 6G edge computing, where nodes play a pivotal role, existing approaches primar-ily emphasize the locality of nodes or clustering relationships between networks. Traditional time-series network modeling tends to fixate on local static relationships, overlooking the dynamic interactions between real network nodes. To address this limitation, we present a model based on time-series interactions, specifically crafted for 6G edge computing networks. Our model extends beyond traditional boundaries, facilitating a comparative analysis of network formation across diverse datasets, presenting a valuable methodology for conducting evolutionary studies. The model's validity is demonstrated through evaluations on two real network datasets. Notably, within the 6G edge, a discernible structure emerges when the preference for high-level nodes surpasses a critical threshold.

关键词： 6G mobile communication Performance evaluation Computational modeling Conferences Computer network reliability Timing Resource management

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Potential of Decentralized Federated Learning in Healthcare: A Comprehensive Survey on Insights and Challenges

Unleashing the Potential of Decentralized Federated Learning...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Haibo Cheng Wenjian Liu Youyang Qu Kexue Fu Qinyuan Wang Faculty of Data Science City University of Macau Macau China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Federated learning (FL) is a distributed learning method that reduces data transmission and privacy risks. However, the existence of a central server may become a target of attackers, resulting in an increased risk of user privacy leakage. The emergence of Decentralized Federated Learning (DFL) is posited to enhance data privacy and system reliability by reducing reliance on central servers and enhancing local data control, especially in the medical field, where personal health data is protected. This research investigates the application of (DFL) in the medical domain, focusing on its limitations. This study employs a systematic literature review, adhering to PRISMA guidelines, to comprehensively understand DFL’s current landscape and challenges in healthcare. The key findings highlight four principal obstacles faced by DFL: security and privacy, communication efficiency, data and model heterogeneity, and incentive mechanisms. It also explores the potential for DFL to facilitate personalized healthcare treatments by large datasets distributed across various medical institutions. This research fills a significant void by systematically reviewing DFL technologies in healthcare. It provides insights into applications, challenges, and future directions for participants seeking secure and efficient healthcare data handling.

关键词： Surveys Data privacy Systematics Federated learning Medical services Data models Servers security Reliability Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events

EventTrojan: Manipulating Non-Intrusive Speech Quality Asses...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ying Ren Kailai Shen Zhe Ye Diqun Yan Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Juphoon System Software Co. Ltd Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Non-Intrusive speech quality assessment (NISQA) has gained significant attention for predicting speech’s mean opinion score (MOS) without requiring the reference speech. Researchers have gradually started to apply NISQA to various practical scenarios. However, little attention has been paid to the security of NISQA models. Backdoor attacks represent the most serious threat to deep neural networks (DNNs) due to the fact that backdoors possess a very high attack success rate once embedded. However, existing backdoor attacks assume that the attacker actively feeds samples containing triggers into the model during the inference phase. This is not adapted to the specific scenario of NISQA. And current backdoor attacks on regression tasks lack an objective metric to measure the attack performance. To address these issues, we propose a novel backdoor triggering approach (EventTrojan) that utilizes an event during the usage of the NISQA model as a trigger. Moreover, we innovatively provide an objective metric for backdoor attacks on regression tasks. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the EventTrojan attack. Besides, it also has good resistance to several defense methods.

关键词： Measurement Resistance Adaptation models Multimedia systems Current measurement Artificial neural networks Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

SRIF: Data-Free Knowledge Distillation via Stable Regulation and Input Filtering

引用

IEEE Transactions on Multimedia 2025年

作者： Zhang, Zherui Xu, Rongtao Wang, Changwei Xu, Shibiao Zhou, Jie Xu, Wenhao Gao, Longxiang Xu, Wenbo Guo, Li Beijing University of Posts and Telecommunications School of Artificial Intelligence Beijing China Chinese Academy of Sciences State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Beijing China Qilu University of Technology Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Jinan China

Data-free knowledge distillation (DFKD) enables knowledge transfer from a pre-trained teacher to a student network without accessing the real dataset. However, generator-based DFKD methods struggle to ensure that the synthetic images accurately reflect the real dataset distribution. The update of the generator network relies heavily on teacher category guidance, but varying teacher prediction accuracy across categories leads to inconsistent synthetic image quality. Such variations introduce a distribution shift between synthetic and real datasets, negatively impacting student network performance during knowledge distillation. To address this challenge, we propose the SRIF, comprising two components: Student-Driven Flexible Filtering (SDFF) and Re-weighting for Independent Regularization (RIR). SDFF filters out synthetic images affected by the category distribution shift during data generation, producing a more reliable dataset. RIR, applied during distillation, encourages the student to learn stable causal relationships through sample reweighting. Both components flexibly integrate into existing DFKD frameworks, improving performance while reducing training costs. © 1999-2012 IEEE.

关键词： Data-Free Knowledge Distillation Distribution Shift Stable Prediction

来源：评论

学校读者我要写书评

暂无评论

A Secure keyword Spotting Scheme Based on Complex Residual network

A Secure Keyword Spotting Scheme Based on Complex Residual N...

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Jingyi Chen Xiangyu Gao Peijia Zheng Huiyu Zhou Jian Li Dong Wei Jianbin Zou School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Nanning China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) Jinan China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China Amazon Web Services Beijing China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

To address the privacy risks associated with intelligent voice assistants, this paper proposes a non-interactive, end-to-end keyword spotting scheme in the encrypted domain. The scheme introduces an innovative complex-valued residual neural network (CR-NN) and leverages low-degree polynomial approximations to enable encrypted computation of complex activation functions. By supporting single instruction multiple data (SIMD) operations, the scheme significantly enhances computational efficiency while reducing ciphertext size. Experimental results demonstrate that the proposed method outperforms existing approaches across multiple performance metrics, balancing efficient keyword spotting with robust privacy protection and offering new insights for the application of deep learning in the encrypted domain.

关键词： Deep learning Measurement Privacy Single instruction multiple data Image processing Personal voice assistants Polynomials Cryptography Protection Residual neural networks

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：