检索结果-内蒙古大学图书馆

1st Workshop on GenAI Content Detection, GenAIDetect 2025

作者： Jiao, Kaijie Yao, Xingyu Ma, Shixuan Fang, Sifan Guo, Zikang Xu, Benfeng Zhang, Licheng Wang, Quan Zhang, Yongdong Mao, Zhendong University of Science and Technology of China Hefei China MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9798891762053

This paper presents the approach we proposed for GenAI Detection Task 2, which aims to classify a given text as either machine-generated or human-written, with a particular emphasis on academic essays. We participated in subtasks A and B, which focus on detecting English and Arabic essays, respectively. We propose a simple and efficient method for detecting machine-generated essays, where we use the Llama-3.18B as a proxy to capture the essence of each token in the text. These essences are processed and classified using a refined feature classification network. Our approach does not require fine-tuning the LLM. Instead, we leverage its extensive multilingual knowledge acquired during pretraining to significantly enhance detection performance. The results validate the effectiveness of our approach and demonstrate that leveraging a proxy model with diverse multilingual knowledge can significantly enhance the detection of machine-generated text across multiple languages, regardless of model size. In Subtask A, we achieved an F1 score of 99.9%, ranking first out of 26 teams. In Subtask B, we achieved an F1 score of 96.5%, placing fourth out of 22 teams, with the same score as the third-place team. © 2025 International Conference on Computational Linguistics.

关键词： Knowledge acquisition

来源：评论

学校读者我要写书评

暂无评论

LayerCFL:an efcient federated learning with layer-wised clustering

引用

Cybersecurity 2025年第1期8卷 72-85页

作者： Jie Yuan Rui Qian Tingting Yuan Mingliang Sun Jirui Li Xiaoyong Li School of Cyberspace Security Beijing University of Posts and TelecommunicationsBeijingChina Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijingChina Institute of Computer Science Faculty of Mathematics and Computer ScienceUniversity of GoettingenGöettingenGermany School of Information Technology Henan University of Chinese MedicineZhengzhouHenanChina

Federated Learning(FL)sufers from the Non-IID problem in practice,which poses a challenge for efcient and accurate model *** address this challenge,prior research has introduced clustered FL(CFL),which involves clustering clients and training them *** its potential benefts,CFL can be computationally and communicationally expensive when the data distribution is unknown *** is because CFL involves the entire neural networks of involved clients in computing the clusters during training,which can become increasingly timeconsuming with large-sized *** tackle this issue,this paper proposes an efcient CFL approach called LayerCFL that employs a Layer-wised clustering *** LayerCFL,clients are clustered based on a limited number of layers of neural networks that are pre-selected using statistical and experimental *** experimental results demonstrate the efectiveness of LayerCFL in mitigating the impact of Non-IID data,improving the accuracy of clustering,and enhancing computational efciency.

关键词： Federated learning Clustered federated learning Non-IID Layer-wised clustering

来源：评论

学校读者我要写书评

暂无评论

EHealth: A Chinese Biomedical Language Model Built via Multi-Level Text Discrimination

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 908-921页

作者： Quan Wang Songtai Dai Benfeng Xu Yajuan Lyu Hua Wu Haifeng Wang MOE Key Laboratory of Trustworthy Distributed Computing and Service Beijing University of Posts and Telecommunications Beijing China Baidu Inc. Beijing China School of Information Science and Technology University of Science and Technology of China Hefei China

Pre-trained language models (PLMs) have recently revolutionized the field of natural language processing, impacting not only the general domain but also the biomedical domain. Most previous studies on constructing biomedical PLMs relied simply on domain adaptation and focused mainly on English. This work introduces eHealth, a compact, encoder-based Chinese biomedical PLM that can be fine-tuned in a customized manner to effectively handle various Chinese biomedical language understanding tasks. Rather than relying on domain adaptation, eHealth is built from scratch using a novel pre-training framework. This framework trains eHealth as a discriminator through token- and sequence-level discrimination. Token-level discrimination detects corrupted input tokens and recovers their original forms from plausible candidates, while sequence-level discrimination further distinguishes corruptions of the same original sequence from those of others. As a result, eHealth can learn language semantics at both token and sequence levels. Moreover, eHealth is trained entirely from scratch with a newly constructed in-domain vocabulary, which may help improve tokenization and understanding of biomedical text. Extensive experiments on 11 Chinese biomedical language understanding tasks of various forms verify the effectiveness and superiority of eHealth. The pre-trained model as well as the code have been released to the public.

关键词： Biological system modeling Electronic healthcare Adaptation models Vocabulary Encoding Generators Bidirectional control Training Computational modeling Speech processing

来源：评论

学校读者我要写书评

暂无评论

Novelty Calculation in Imbalanced Dynamic Interconnected Specialized IoT Network Traffic

引用

IEEE Internet of Things Journal 2025年

作者： Fan, Mingrui Zuo, Jinxin Gao, Jiaqi He, Yaru Shi, Weidong Lu, Yueming Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing100876 China Beijing University of Posts and Telecommunications School of Information and Communication Engineering Beijing100876 China

Quantifying the deviation of testing samples from known benign traffic in the form of novelty scores is essential for identifying new malicious traffic and detecting concept drifts of benign traffic. Most existing solutions generate novelty scores based on the outputs from the supervised neural network's last layers. However, the performance of these supervised techniques is significantly compromised in the unbalanced dynamic interconnected specialized IoT network traffic such as Electronic Power Grid. To solve this challenge, we investigate an improved novelty score calculation approach. It employs the targeted distance loss to ensure that different known classes form class-specific, dense clusters within the embedding space outputted by the neural network. The minimum distance between the testing sample and the centers of each known class is utilized as the novelty score. Extensive comparison experiments on public datasets and real Electronic Power Grid traffic demonstrate that our approach outperforms existing supervised techniques. As the imbalance in known class distributions increases, our proposed method consistently achieves higher AUROC and AUPR than baselines, with a reduced FPR95. This study analyzes imbalanced known class distributions' negative impact on novelty detection and provides practical improvement. © 2014 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Multi-holder Role and Strange Attractor-Based Data Possession Proof in Medical Clouds 24th

A Multi-holder Role and Strange Attractor-Based Data Possess...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Guo, Jinyuan Sun, Lijuan Wu, Jingchen Chu, Chiawei Gao, Yutong Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing China School of Cybersecurity Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance Ministry of Education Minzu University Beijing China Intellectual Property Information Service Center BHU Beihang University Beijing China City University of Macau Taipa China Li’an International Education Innovation Pilot Zone Hainan International College of Minzu University of China Hainan Beijing China

ISBN: (纸本)9789819615278

Proof of Data Possession is a technique for ensuring the integrity of data stored in cloud storage. However, most audit schemes assume only one role for data owners, which is not suitable for complex Smart Healthcare Network with multiple roles. In such schemes addressing the risk of third-party auditors (TPA) colluding with other entities, blockchain is typically employed. However, this necessitates extensive computation, resulting in unacceptably high energy consumption and prolonged verification times. In this paper, we propose a Proof of Data Possession scheme tailored for medical network environments, which incorporates protocols designed for both healthcare professionals and patients, considering the diverse roles that generate data within medical network applications and the varying performance of the devices they use. During the generation of metadata for verification, the protocol incorporates the varying security risk levels associated with medical data. For subsequent metadata selection, an audit block extraction strategy based on strange attractors is employed, effectively mitigating the risk of collusion by third-party TPA, thereby enhancing the security and efficiency of the scheme. Additionally, we conducted experimental analysis and comparisons, demonstrating higher security and practical applicability. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Unveiling the secrets without data: can graph neural networks be exploited through data-free model extraction attacks? 24

Unveiling the secrets without data: can graph neural network...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Yuanxin Zhuang Chuan Shi Mengmei Zhang Jinghui Chen Lingjuan Lyu Pan Zhou Lichao Sun Beijing University of Posts and Telecommunications Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education The Pennsylvania State University SONY AI Huazhong University of Science and Technology Lehigh University

ISBN: (纸本)9781939133441

Graph neural networks (GNNs) play a crucial role in various graph applications, such as social science, biology, and molecular chemistry. Despite their popularity, GNNs are still vulnerable to intellectual property threats. Previous studies have demonstrated the susceptibility of GNN models to model extraction attacks, where attackers steal the functionality of GNNs by sending queries and obtaining model responses. However, existing model extraction attacks often assume that the attacker has access to specific information about the victim model's training data, including node attributes, connections, and the shadow dataset. This assumption is impractical in real-world scenarios. To address this issue, we propose STEAL-GNN, the first data-free model extraction attack framework against GNNs. STEALGNN advances prior GNN extraction attacks in three key aspects: 1) It is completely data-free, as it does not require actual node features or graph structures to extract GNN models. 2) It constitutes a full-rank attack that can be applied to node classification and link prediction tasks, posing significant intellectual property threats across a wide range of graph applications. 3) It can handle the most challenging hard-label attack setting, where the attacker possesses no knowledge about the target GNN model and can only obtain predicted labels through querying the victim model. Our experimental results on four benchmark graph datasets demonstrate the effectiveness of STEALGNN in attacking representative GNN models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Compositional Concept-Based Neuron-Level Interpretability for Deep Reinforcement Learning

arXiv

引用

arXiv 2025年

作者： Jiang, Zeyu Huang, Hai Zuo, Xingquan School of Computer Science Beijing University of Posts and Telecommunications Beijing China Key Laboratory of Trustworthy Distributed Computing and Services Ministry of Education Beijing China

Deep reinforcement learning (DRL), through learning policies or values represented by neural networks, has successfully addressed many complex control problems. However, the neural networks introduced by DRL lack interpretability and transparency. Current DRL interpretability methods largely treat neural networks as black boxes, with few approaches delving into the internal mechanisms of policy/value networks. This limitation undermines trust in both the neural network models that represent policies and the explanations derived from them. In this work, we propose a novel concept-based interpretability method that provides fine-grained explanations of DRL models at the neuron level. Our method formalizes atomic concepts as binary functions over the state space and constructs complex concepts through logical operations. By analyzing the correspondence between neuron activations and concept functions, we establish interpretable explanations for individual neurons in policy/value networks. Experimental results on both continuous control tasks and discrete decision-making environments demonstrate that our method can effectively identify meaningful concepts that align with human understanding while faithfully reflecting the network’s decision-making logic. Copyright © 2025, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Ranking Modules for Integrate Testing Based on PageRank Algorithm

引用

Chinese Journal of Electronics 2017年第5期26卷 993-998页

作者： SUN Qi Krishna Ricky MONIZ YUAN Yuyu Key Laboratory of Trustworthy Distributed Computing and Service(BUPT) Ministry of EducationBeijing University of Posts and Telecommunications

The testing industry need to prioritize the limited resources and focus on testing modules whose failure is mostly likely to cause *** paper discusses a method that can rank modules in a software package for integrate testing using the PageR ank *** this algorithm,a sequences of random walks iteratively can find a high likelihood of encountering a node,which is interpreted as it being an important performance *** experiment result prove that the proposed method actually can be used to prioritize testing of specific modules when testing resource are scarce.

关键词： Software testing Integrate testing PageRank algorithm Testing prioritize

来源：评论

学校读者我要写书评

暂无评论

An Alternative-service Recommending Algorithm Based on Semantic Similarity

引用

China Communications 2017年第8期14卷 124-136页

作者： Kun Guo Yonghua Li Yueming Lu Key Laboratory of Trustworthy Distributed Computing and Service Ministry of EducationBeijing University of Posts and TelecommunicationsBeijingChina

With the development of the Internet of Things(Io T), people's lives have become increasingly convenient. It is desirable for smart home(SH) systems to integrate and leverage the enormous information available from IoT. Information can be analyzed to learn user intentions and automatically provide the appropriate services. However, existing service recommendation models typically do not consider the services that are unavailable in a user's living environment. In order to address this problem, we propose a series of semantic models for SH devices. These semantic models can be used to infer user intentions. Based on the models, we proposed a service recommendation probability model and an alternative-service recommending algorithm. The algorithm is devoted to providing appropriate alternative services when the desired service is unavailable. The algorithm has been implemented and achieves accuracy higher than traditional Hidden Markov Model(HMM). The maximum accuracy achieved is 68.3%.

关键词： activity recognition semantic model service recommendation unavailable service

来源：评论

学校读者我要写书评

暂无评论

DropConnect Regularization Method with Sparsity Constraint for Neural Networks

引用

Chinese Journal of Electronics 2016年第1期25卷 152-158页

作者： LIAN Zifeng JING Xiaojun WANG Xiaohan HUANG Hai TAN Youheng CUI Yuanhao Key Laboratory of Trustworthy Distributed Computing and Service (BUPT) Ministry of Education Beijing University of Posts and Telecommunications School of Software and Microelectronics Peking University

Drop Connect is a recently introduced algorithm to prevent the co-adaptation of feature *** to Dropout, Drop Connect gains state-of-the-art results on several image recognition benchmarks. Motivated by the success of Drop Connect, we extended this algorithm with the ability of sparse feature selection. In Drop Connect algorithm, the dropping masks of weights are generated using Bernoulli gating variables that are independent of the weights and activations. We introduce a new strategy to generate masks depending on the outputs of previous layer. Using this method, neurons which are promising to produce sparser features will be assigned a bigger possibility to keep active in the forward and backward propagations. We then evaluate such sparsity constrained Drop Connect on MNIST and CIFAR datasets in comparison with ordinary Drop Connect and Dropout method. The results show that our new method improves the sparsity of features significantly, while not degrading the precision.

关键词： Drop Connect Sparse regularization Deep learning 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：