检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Mei Zhu, Xiaojie Hu, Ruimin Zhu, Dongliang Liao, Liang Ye, Mang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China School of Cyber Science and Engineering Wuhan University Whuhan China Cyberspace Security Laboratory School of Network and Information Security Xidian University Xi'an China The School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Fatigue is a critical factor contributing to accidents in industries such as safety monitoring and engineering construction. Fatigue exhibits dynamic complexity and non-stationary characteristics, so there are many intermediate states of short-term variation between alert and fatigue. Capturing and learning the signs of these intermediate states is essential for accurate fatigue assessment. However, current fatigue detection methods primarily rely on coarse-grained labels, typically spanning minutes to hours, and commonly treat alert and fatigue as two distinctly separate distributions, overlooking the expression of intermediate states and oversimplifying the rich distribution information of fatigue types and levels, thereby limiting detection effectiveness. To address these, this paper explores a refined representation of fatigue in terms of three dimensions: time, type, and level, and proposes a MultiDimensional Fine-Grained Modeling for Fatigue Detection (MDFG). This introduces the SmallLoss to extract trustworthy samples, utilizes clustering to identify diverse subtypes under alert and fatigued states, and establishes base class sets in each state. Subsequently, a complete base class set containing intermediate state bases is constructed using the base class synthesis method, which achieves the expression of intermediate fatigue states from absence to presence. Finally, fatigue levels are quantified based on the matching between samples and the complete base class set. Moreover, to cope with the complex variability of fatigue states, MDFG employs meta-learning for training. MDFG achieves an Average accuracy improvement of 10.0% and 12.1% on two real datasets compared to methods that do not consider fine-grained information. Extensive experiments demonstrate that the MDFG exhibits superior robustness and stability among current fatigue detection methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserv

关键词： Safety factor

来源：评论

学校读者我要写书评

暂无评论

Breaking Speaker Recognition with Paddingback

Breaking Speaker Recognition with Paddingback

引用

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

作者： Zhe Ye Diqun Yan Li Dong Kailai Shen Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology China

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent research has shown that speech backdoors can utilize transformations as triggers, similar to image backdoors. However, human ears can easily be aware of these transformations, leading to suspicion. In this paper, we propose PaddingBack, an inaudible backdoor attack that utilizes malicious operations to generate poisoned samples, rendering them indistinguishable from clean ones. Instead of using external perturbations as triggers, we exploit the widely-used speech signal operation, padding, to break speaker recognition systems. Experimental results demonstrate the effectiveness of our method, achieving a significant attack success rate while retaining benign accuracy. Furthermore, Padding-Back demonstrates the ability to resist defense methods and maintain its stealthiness against human perception.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Attribute-Based Data Sharing Scheme with Flexible Search Functionality for Cloud-Assisted Autonomous Transportation System

引用

IEEE Transactions on Industrial Informatics 2023年第11期19卷 10977-10986页

作者： Xiong, Hu Wang, Hanxiao Meng, Weizhi Yeh, Kuo-Hui University of Electronic Science and Technology of China School of Information and Software Engineering Network and Data Security Key Laboratory of Sichuan Province Chengdu610054 China Advanced Cryptography and System Security Key Laboratory of Sichuan Province Chengdu610025 China Technical University of Denmark Department of Applied Mathematics and Computer Science Kongens Lyngby2800 Denmark National Dong Hwa University Department of Information Management Hualien97401 Taiwan National Sun Yat-sen University Department of Computer Science and Engineering Kaohsiung804201 Taiwan

The existing group public key encryption with equality test schemes could only support one-to-one data sharing and are not suitable for cloud-assisted autonomous transportation systems, which demand one-to-many data sharing. To tackle this problem efficiently, in this article, we put forward the group-attribute-based encryption with equality test (G-ABEET) scheme. The presented G-ABEET allows sensors equipped in vehicles to encrypt traffic data with an expressive access policy before sharing it. Only users with attributes required by the access policy ought to access the shared ciphertexts, thus achieving selective one-to-many data sharing. Meanwhile, the authorized cloud server could provide group users with equality tests over the ciphertexts, realizing ciphertext search ability. Furthermore, with the group mechanism, the G-ABEET scheme could resist offline message recovery attacks. Besides, in the standard model, we give rigorous security proof of the G-ABEET construction. The feasibility and efficiency of G-ABEET are demonstrated by experimental simulations. © 2005-2012 IEEE.

关键词： Cloud computing

来源：评论

学校读者我要写书评

暂无评论

THC-DL: Three-Party Homomorphic Computing Delegation Learning for Secure Optimization

引用

IEEE Internet of Things Journal 2025年

作者： Yang, Ze Tian, Youliang Xiong, Jinbo Niu, Kun Li, Mengqian Zhang, Xinyu Ma, Jianfeng Guizhou University Guizhou Provincial Key Laboratory of Cryptography and Blockchain Technology College of Computer Science and Technology Guiyang550025 China Guizhou University College of Big Data and Information Engineering Guiyang550025 China Fujian Normal University Fujian Provincial Key Laboratory of Network Security and Cryptology College of Computer and Cyber Security Fuzhou350117 China Xidian University State Key Laboratory of Integrated Services Network Xi’an710071 China Xidian University State Key Laboratory of Integrated Services Network School of Cyber Engineering Xi’an710071 China

Delegation Learning(DL) flourishes data sharing, enabling agents to delegate data to the cloud for model training. To preserve privacy, homomorphic encryption (HE) offers an effective solution for privacy-preserving machine learning (PPML) in delegation learning, yet faces critical challenges in functionality (non-linear activation support), practicality (ciphertext blow-up from iterative computations), and security (data leakage risks caused by public knowledge of the mathematical principles applied in model training). To tackle these challenges, we propose THC-DL, a three-party HE framework addressing these challenges holistically for the first time. We elaborately design the ciphertext secure comparison (DL-CSC) protocol to satisfy secure comparison with private inputs, enabling efficient non-linear operations with O(1) communication complexity that reduces runtime to 12.5% of the DGK (Dolev-Greensmith-Kent protocol, the well-known comparison protocol). Second, we construct a Truncation-Mapping (Tru-Map) scheme, a mechanism that transforms input data by truncating and mapping it into a domain that facilitates more efficient processing, and the addition of truncated mapped data to resolve ciphertext blow-up by adaptively scaling ciphertexts during iterative training, ensuring correctness. Third, we formalize data leakage risks in HE-based quadratic convex optimization (standard in ML) and apply THC-DL to construct a secure optimization scheme. Theoretical analysis confirms THC-DL’s resilience against input recovery attacks, even when adversaries exploit public model parameters. Experiments on a real-world platform validate DL-CSC’s efficiency and scalability while reducing the computational complexity and communication complexity from O(n) to O(1) where n denotes the length of the input bits. © 2014 IEEE.

关键词： Convex optimization

来源：评论

学校读者我要写书评

暂无评论

A Web Attack Detection Method Based on DistilBERT and Feature Fusion for Power Micro-Application Server 2

A Web Attack Detection Method Based on DistilBERT and Featur...

引用

2nd International Conference on Advanced Electronics, Electrical and Green Energy, AEEGE 2023

作者： Nige, Li Lu, Chen Lei, Zhao Zhenning, Teng Zhiqiang, Wang Yiyang, Shao Xiaolin, Gui State Grid Laboratory of Power Cyber-Security Protection and Monitoring Technology State Grid Smart Grid Research Institute Co.Ltd. Nanjing China Xi'an Jiaotong University Faculty of Electronic and Information Engineering Shaanxi Province Key Laboratory of Computer Network Xi'an China

ISBN: (纸本)9798350322866

The widespread use of power micro-applications has significantly expanded the attack surface of their server side, thus increasing the risk of vulnerability attacks such as SQL injection, XSS, and CRLF injection. To ensure the security of power systems, these attacks must be detected precisely and timely. Therefore, this paper proposes a server-side web attack detection method based on DistilBERT and feature fusion for HTTP and HTTPS requests. The method treats HTTP and HTTPS requests as text data, specifically, extracts deep semantic features using DistilBERT, and fuses them with well-designed empirical features to comprehensively characterize and classify the request. Consequently, anomalous requests can be detected. The experimental results show that the accuracy, precision, recall, and F1 score of the method on HTTP CSIC 2010 and FWAF datasets are close to or higher than 99%. Compared with other methods as far as we known, this method has better performance and efficiency. © 2023 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Vision-language models are strong noisy label detectors 24

Vision-language models are strong noisy label detectors

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Tong Wei Hao-Tian Li Chun-Shu Li Jiang-Xin Shi Yu-Feng Li Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China and National Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Engineering Southeast University Nanjing China and Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education China National Key Laboratory for Novel Software Technology Nanjing University China and School of Artificial Intelligence Nanjing University China

ISBN: (纸本)9798331314385

Recent research on fine-tuning vision-language models has demonstrated impressive performance in various downstream tasks. However, the challenge of obtaining accurately labeled data in real-world applications poses a significant obstacle during the fine-tuning process. To address this challenge, this paper presents a Denoising Fine-Tuning framework, called DEFT, for adapting vision-language models. DEFT utilizes the robust alignment of textual and visual features pre-trained on millions of auxiliary image-text pairs to sieve out noisy labels. The proposed framework establishes a noisy label detector by learning positive and negative textual prompts for each class. The positive prompt seeks to reveal distinctive features of the class, while the negative prompt serves as a learnable threshold for separating clean and noisy samples. We employ parameter-efficient fine-tuning for the adaptation of a pre-trained visual encoder to promote its alignment with the learned textual prompts. As a general framework, DEFT can seamlessly fine-tune many pre-trained models to downstream tasks by utilizing carefully selected clean samples. Experimental results on seven synthetic and real-world noisy datasets validate the effectiveness of DEFT in both noisy label detection and image classification tasks. Our source code is available at https://***/HotanLee/DeFT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Efficient and Interpre Table Speech Enhancement network Via Deep Dictionary Learning

An Efficient and Interpre Table Speech Enhancement Network V...

引用

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

作者： Xinmeng Xu Yiqun Zhang Weiping Tu Yuhong Yang NERCMS School of Computer Science Wuhan University China Hubei Luojia Laboratory China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Speech enhancement is a vital and highly ill-posed problem for many speech downstream tasks. While currently existing deep learning based speech enhancement methods have held state-of-the-art results, they still possess apparent shortcomings in that most of the deep learning based models lack interpretability. This deficiency results in unsatisfied speech enhancement performance in many sophisticated scenarios. To tackle this problem, we integrate dictionary learning and sparse coding into deep learning networks for speech enhancement and present a deep dictionary learning based speech enhancement network (DicLSENet). Specifically, the proposed DicLSENet strictly follows the principle of dictionary learning, learns the priors for both representation coefficients and dictionaries, and adaptively adjusts the dictionary for each input. Experimental results show that the proposed model outperforms state-of-the-art fully deep learning based methods with attractive computational costs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Parallelizable Counterfactual Generation Method Based on Gradient Optimization 29

A Parallelizable Counterfactual Generation Method Based on G...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Ding, Haorun Jiang, Xuesong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Shandong Academy of Sciences Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology 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 State Key Laboratory of High-end Server and Storage Technology Jinan China

ISBN: (纸本)9798350330717

Post-hoc explanations are important for people to understand the predictions of explanation models. One class of methods in post-hoc explanation is the generation of counterfactuals, where a hypothetical example is obtained by perturbing the inputs to show how one could obtain a different prediction from the decision model. Counter-factual explanations should satisfy several properties: One is that counterfactuals generated under specific scenarios and constraints should be feasible for users, i.e., they should accommodate different causal constraints. The other is that it is more desirable for users to have a wider variety of viable examples, i.e., counterfactual diversity. To this end, we propose a parallelizable method based on gradient optimization. We partition the input feasible domains, perform counterfactual generation independently for each feasible domain, and then parallelize the counterfactual generation process for each feasible domain. Experimental results show that our approach effectively improves the diversity, sparsity, and proximity of the generated counterfactual instances on the public datasets Adult-Income, Lending-Club, German-Credit, and COMPAS compared to other models. © 2023 IEEE.

关键词： counterfactual explanation machine learning parallel computing

来源：评论

学校读者我要写书评

暂无评论

Curricular Contrastive Regularization for Speech Enhancement with Self-Supervised Representations

Curricular Contrastive Regularization for Speech Enhancement...

引用

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

作者： Xinmeng Xu Chang Han Yiqun Zhang Weiping Tu Yuhong Yang NERCMS School of Computer Science Wuhan University China Hubei Luojia Laboratory China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China

Existing deep learning-based speech enhancement methods only adopt clean speech as positive samples to guide the training of speech enhancement networks while negative samples, i.e., noisy speech, are unexploited. In this paper, we adopt contrastive regularization (CR) built upon contrastive learning to exploit both the information of noisy and clean speech as negative and positive samples, respectively. Particularly, CR minimizes the distance between clean and enhanced speech and maximizes the distance between noisy and enhanced speech in the representation space of the self-supervised learning model. However, the contrastive samples are non-consensual, as the negatives are usually represented distantly from the clean speech, leaving the solution space still under-constricted. To tackle this issue, we provide the negative samples assembled from (1) the noisy speech, and (2) the corresponding enhanced speech without using CR, and we customize a curriculum learning strategy to define the importance of these negative samples to balance the learning difficulty caused by different similarities between the embeddings of the positive and negative samples. Experiments show that our proposal improves SE performance effectively without introducing additional computation/parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Responding to News Sensitively in Stock Attention networks via Prompt-Adaptive Trimodal Model

引用

IEEE Transactions on Neural networks and Learning Systems 2025年第6期36卷 10099-10113页

作者： Haotian Liu Bowen Hu Yadong Zhou Yuxun Zhou Ministry of Education Key Laboratory for Intelligent Networks and Network Security Faculty of Electronic and Information Engineering Xi’an Jiaotong University Xi’an Shaanxi China Department of Electrical Engineering and Computer Sciences University of California at Berkeley Berkeley CA USA

Modern quantitative finance and portfolio-based investment hinge on multimedia news and historical price trends for stock movement prediction. However, prior studies overlook the long tail effect in the feature distribution of stocks, inevitably leading to biased attention and thus degrading the efficiency of utilizing news. To this end, we propose a prompt-adaptive trimodal model (PA-TMM) to overcome the biased stock attention networks and tail feature scarcity problem. In this model, sentiments automatically extracted from trimodal information serve as prompts reflecting the market’s collective mood for other entities, and the interactions among stocks are dynamically inferred for integrating both news- and price-induced movements. By leveraging the movement prompt adaptation (MPA) strategy, our model proactively adapts to the feature-imbalanced phenomenon and converges toward being responsive to the news sensitively. Extensive experiments conducted on real-world datasets consistently demonstrate not only the superiority of the proposed framework over various state-of-the-art baselines, but also its effectiveness, profitability, and robustness in Fintech. The code is accessible at https://***/lauht/PA-TMM .

关键词： Adaptation models Peer-to-peer computing Investment Heavily-tailed distribution Tail Stock markets Feature extraction Correlation Attention mechanisms Time series analysis

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：