检索结果-内蒙古大学图书馆

Privacy-preserving explainable AI: a survey

Science China(information Sciences) 2025年第1期68卷 23-56页

作者： Thanh Tam NGUYEN Thanh Trung HUYNH Zhao REN Thanh Toan NGUYEN Phi Le NGUYEN Hongzhi YIN Quoc Viet Hung NGUYEN School of Information and Communication Technology Griffith University School of Computer and Communication Sciences Ecole Polytechnique Federale de Lausanne Faculty of Mathematics and Computer Science University of Bremen Faculty of Information Technology HUTECH University Department of Computer Science Hanoi University of Science and Technology School of Electrical Engineering and Computer Science The University of Queensland

As the adoption of explainable AI(XAI) continues to expand, the urgency to address its privacy implications intensifies. Despite a growing corpus of research in AI privacy and explainability, there is little attention on privacy-preserving model explanations. This article presents the first thorough survey about privacy attacks on model explanations and their countermeasures. Our contribution to this field comprises a thorough analysis of research papers with a connected taxonomy that facilitates the categorization of privacy attacks and countermeasures based on the targeted explanations. This work also includes an initial investigation into the causes of privacy leaks. Finally, we discuss unresolved issues and prospective research directions uncovered in our analysis. This survey aims to be a valuable resource for the research community and offers clear insights for those new to this domain. To support ongoing research, we have established an online resource repository, which will be continuously updated with new and relevant findings.

关键词： privacy-preserving explainable AI privacy attacks privacy defences PrivEx PPXAI

来源：评论

学校读者我要写书评

暂无评论

Research Progress in Solar Flare Prediction Methods

引用

Research in Astronomy and Astrophysics 2025年第3期25卷 280-309页

作者： Ke Han Zhen Liu Xian-Yi Zhao Yi-Fei Li De-Quan Zheng Jie Wan School of Computer and Information Engineering Harbin University of Commerce Faculty of Computing Harbin Institute of Technology School of Energy Science and Engineering Harbin Institute of Technology

Solar flares are one of the strongest outbursts of solar activity,posing a serious threat to Earth’s critical infrastructure,such as communications,navigation,power,and ***,it is essential to accurately predict solar flares in order to ensure the safety of human ***,the research focuses on two directions:first,identifying predictors with more physical information and higher prediction accuracy,and second,building flare prediction models that can effectively handle complex observational *** terms of flare observability and predictability,this paper analyses multiple dimensions of solar flare observability and evaluates the potential of observational parameters in *** flare prediction models,the paper focuses on data-driven models and physical models,with an emphasis on the advantages of deep learning techniques in dealing with complex and high-dimensional *** reviewing existing traditional machine learning,deep learning,and fusion methods,the key roles of these techniques in improving prediction accuracy and efficiency are *** prevailing challenges,this study discusses the main challenges currently faced in solar flare prediction,such as the complexity of flare samples,the multimodality of observational data,and the interpretability of *** conclusion summarizes these findings and proposes future research directions and potential technology advancement.

关键词： (Sun:) sunspots magnetohydrodynamics (MHD) Sun: activity Sun: flares Sun: magnetic fields

来源：评论

学校读者我要写书评

暂无评论

Classification of human-written and AI-generated sentences using a hybrid CNN-GRU model optimized by the spotted hyena algorithm

引用

Alexandria engineering Journal 2025年 126卷 116-130页

作者： Ragab, Mahmoud Ashary, Ehab Bahaudien Kateb, Faris Hakeem, Abeer Mosli, Rayan Albogami, Nasser N. Nooh, Sameer Information Technology Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Electrical and Computer Engineering Department Faculty of Engineering King Abdulaziz University Jeddah21589 Saudi Arabia Information Systems Department Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

The rapid advancement of artificial intelligence (AI) in generating human-like text poses significant challenges in distinguishing between human-written and AI-generated content. Recent advancements in natural language generation have significantly enhanced the quality and variety of AI-generated text, making it almost indistinguishable from human-written content. ChatGPT, a popular AI model, belongs to the generative pre-trained transformer family. While human content is created with a clear intent to convey meaning, AI-generated text aims to replicate human-like language. Classifying human-written and AI-generated sentences is crucial for addressing issues like fake news, plagiarism, and spamming. AI text often follows repetitive patterns, while human writing is more creative and original, making detection significant for combating misinformation. Therefore, this study proposes to classify human-written and AI-generated sentences using a hybrid CNN-GRU model optimized by the Spotted Hyena Algorithm (CHWAIG-DLSHO) approach. The approach involves preprocessing text data through tokenization, lemmatization, and data splitting, followed by word embedding using Latent Dirichlet Allocation (LDA). A hybrid convolutional neural network (CNN) and gated recurrent unit (GRU) model is employed for sentence classification. The spotted hyena optimizer (SHO) model is utilized to fine-tune the hyperparameters of the CNN-GRU model, enhancing its performance. The analysis of the CHWAIG-DLSHO method takes place utilizing AI vs. human text dataset. The performance validation of the CHWAIG-DLSHO method portrayed a superior accuracy value of 99.17 % over existing techniques. © 2025 The Authors

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

JLOS: a Cooperative UAV-Based Optical Wireless Communication With Multi-Agent Reinforcement Learning

引用

IEEE Transactions on Network and Service Management 2025年第2期22卷 1345-1356页

作者： Liu, Jiangang Luo, Hanjiang Tao, Hang Liu, Jiahong Zhou, Jiehan Shandong University of Science and Technology College of Computer Science and Engineering Qingdao China University of Oulu Faculty of Information Technology and Electrical Engineering Oulu Finland

In maritime Internet of Things (IoT) systems, leveraging a swarm of Unmanned Aerial Vehicles (UAVs) and optical communication can achieve a variety of potential maritime missions. However, due to the high directionality of the optical beam and interference from the marine environment, the optical link via UAVs as relays is prone to interruption. To address this challenge, we propose a Joint Link Optimization Scheme (JLOS) that includes Wind Disturbance Resistance (WDR) and Adaptive Beamwidth Adjustment (ABA). In WDR, we first model the problem as a Partially Observed Markov Decision Process (POMDP), and then design a collaborative Multi-Agent Reinforcement Learning (MARL) approach to control a swarm of UAVs in windy conditions, to maintain mechanical stability and prevent link interruption. Furthermore, in ABA, to reduce uncertainties from control activities and environmental factors like sunlight and fog, we design an adaptive algorithm using distributed MARL. It adjusts beamwidth based on historical UAV locations and link Bit Error Ratio (BER) to improve communication reliability. Numerical simulations confirm its effectiveness in enhancing robust data transmission. © 2004-2012 IEEE.

关键词： Adaptive algorithms

来源：评论

学校读者我要写书评

暂无评论

Abnormal event detection in surveillance videos through LSTM auto-encoding and local minima assistance

引用

Discover Internet of Things 2025年第1期5卷 1-25页

作者： Sengonul, Erkan Samet, Refik Abu Al-Haija, Qasem Alqahtani, Ali Alsemmeari, Rayan A. Alghamdi, Bandar Alturki, Badraddin Alsulami, Abdulaziz A. Department of Computer Engineering Ankara University Ankara06100 Turkey Department of Cybersecurity Faculty of Computer & Information Technology Jordan University of Science and Technology PO Box 3030 Irbid22110 Jordan Department of Networks & Communications Engineering College of Computer Science & Information Systems Najran University Najran61441 Saudi Arabia Department of Information Technology Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia Department of Information Systems Faculty of Computing and Information Technology King Abdulaziz University Jeddah21589 Saudi Arabia

Abnormal event detection in video surveillance is critical for security, traffic management, and industrial monitoring applications. This paper introduces an innovative methodology for anomaly detection in video data, encompassing three primary stages: preprocessing, feature learning, and anomaly detection. We employ background subtraction and noise reduction during preprocessing to refine the data. The feature-learning stage involves training an LSTM autoencoder to capture the essential features of normal video sequences. For anomaly detection, we map video data to a lower-dimensional space (latent code) and compare it against the distribution of codes from normal sequences. We determine regularity scores and identify local minima points exceeding a specified threshold while scrutinizing shadows between adjacent maxima to confirm and pinpoint anomalies. When tested on the CUHK Avenue and UMN datasets, our methodology demonstrated performance with AUCs of 93.8% and 94.1%, respectively, outperforming several baseline models. Our results show the high precision of our method that can detect anomalies, highlighting its potential advantages that it can achieve for enhancing systems of surveillance. © The Author(s) 2025.

关键词： Noise abatement

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence-inspired comprehensive framework for desertification prediction

引用

International Journal of Cognitive Computing in engineering 2025年 6卷 462-476页

作者： Alsubai, Shtwai Mosleh, Mogeeb A.A. Al-Hadhrami, Suheer A. Bhatia, Munish College of Computer Engineering and Sciences Prince Sattam bin Abdulaziz University Alkharj Saudi Arabia Faculty of Engineering & Computing University of Science & Technology Aden Yemen Faculty of Engineering and Information Technology Taiz Univeristy Taiz Yemen Department of Computer Engineering College of Engineering Al Mukalla Hadhramout Yemen Department of Computer Applications National Institute of Technology Kurukshetra India

Desertification greatly affects land deterioration, farming efficiency, economic growth, and health, especially in Gulf nations. Climate change has worsened desertification, making developmental issues in the area even more difficult. This research presents an enhanced framework utilizing the Internet of Things (IoT) for ongoing monitoring, data gathering, and analysis to evaluate desertification patterns. The framework utilizes Bayesian Belief Networks (BBN) to categorize IoT data, while a low-latency processing method on edge computing platforms enables effective detection of desertification trends. The classified data is subsequently analyzed using an Artificial Neural Network (ANN) optimized with a Genetic Algorithm (GA) for forecasting decisions. Using cloud computing infrastructure, the ANN-GA model examines intricate data connections to forecast desertification risk elements. Moreover, the Autoregressive Integrated Moving Average (ARIMA) model is employed to predict desertification over varied time intervals. Experimental simulations illustrate the effectiveness of the suggested framework, attaining enhanced performance in essential metrics: Temporal Delay (103.68 s), Classification Efficacy—Sensitivity (96.44 %), Precision (95.56 %), Specificity (96.97 %), and F-Measure (96.69 %)—Predictive Efficiency—Accuracy (97.76 %) and Root Mean Square Error (RMSE) (1.95 %)—along with Reliability (93.73 %) and Stability (75 %). The results of classification effectiveness and prediction performance emphasize the framework's ability to detect high-risk zones and predict the severity of desertification. This innovative method improves the comprehension of desertification processes and encourages sustainable land management practices, reducing the socio-economic impacts of desertification and bolstering at-risk ecosystems. The results of the study hold considerable importance for enhancing regional efforts in combating desertification, ensuring food security, and formulatin

关键词： Life on land Climate action Desertification Internet of things Artificial neural network

来源：评论

学校读者我要写书评

暂无评论

A Novel 3D Paradigm for Target Expansion of Augmented Reality SSVEP

引用

IEEE Transactions on Neural Systems and Rehabilitation engineering 2025年 33卷 1562-1573页

作者： Cao, Beining Li-Ting Tsai, Charlie Zhou, Nan Do, Thomas Lin, Chin-Teng University of Technology Sydney Computational Intelligence and Brain-Computer Interfaces Laboratory Australian AI Institute Faculty of Engineering and Information Technology School of Computer Science UltimoNSW2007 Australia

Steady-State Visual Evoked Potentials (SSVEP) have proven to be practical in Brain-computer Interfaces (BCI), particularly when integrated with augmented reality (AR) for real-world application. However, unlike conventional computer screen-based SSVEP (CS-SSVEP), which benefits from stable experimental environments, AR-based SSVEP (AR-SSVEP) systems are susceptible to the interference of real-world environment and device instability. Particularly, the performance of AR-SSVEP significantly declines as the target frequency increases. Therefore, our study introduced a 3D paradigm that combines flicker frequency with rotation patterns as stimuli, enabling expansion of target sets without additional frequencies. In the proposed design, in addition to the conventional frequency-based SSVEP feature, bio-marker elicited by visual perception of rotation was investigated. An experimental comparison between this novel 3D paradigm and a traditional 2D approach, which increases targets by adding frequencies, reveals significant advantages. The 12-class 3D paradigm achieved an accuracy of 76.5% and an information transfer rate (ITR) of 70.42 bits/min using 1-second EEG segments. In contrast, the 2D paradigm exhibited a lower performance with 72.07% accuracy and 62.28 bits/min ITR. The result underscores the 3D paradigm’s superiority in enhancing the practical applications of SSVEP-based BCIs in AR settings, especially with shorter time windows, by effectively expanding target recognition without compromising system efficiency. © 2001-2011 IEEE.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Cumulative histogram as a feature selection technique for anomaly detection

引用

Multimedia Tools and Applications 2025年第12期84卷 10095-10107页

作者： Nassar, Mostafa Salama, Rania A. Saleeb, Adel A. El-bahnasawy, Nirmeen A. Ahmed, Hossam Eldin H. Abd El-Samie, Fathi E. Department of Electronics and Electrical Communications Engineering Faculty of Electronic Engineering Menoufia University Menouf32952 Egypt Department of Information Technology Faculty of Computers and Information Suez University Suez Egypt Department of Information Technology College of Computer and Information Sciences Princess Nourah Bint Abdulrahman University Riyadh11671 Saudi Arabia

The enhancement of Intrusion Detection Systems (IDS) is required to ensure protection of network resources and services. This is a hot research topic, especially in the presence of advanced intrusions and attacks. This paper provides a comparison between Distributed Cumulative Histogram (DCH) as a Feature Selection (FS) technique, information Gain Ratio (IGR) FS and wrapper-based FS in terms of accuracy and Root Mean Square Error (RMSE). The utilization of DCH of the traffic instances in normal and attack cases allows us to compare the traffic charts. We can observe the difference between effective features and less effective ones. We verify the feasibility of using DCH as an FS technique in the field of anomaly detection with just six selected features giving more accurate results with most classifiers compared to the IGR and wrapper-based FS. We applied our experiments on the modern UNSW dataset with the WEKA simulation platform that contains a group of classification, feature reduction and selection techniques. © The Author(s) 2024.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Numerical and spatiotemporal features fusion for video summarization

引用

Multimedia Tools and Applications 2025年 1-16页

作者： Aboelenien, Mohamed Salem, Mohammed A.-M. Faculty of Media Engineering and Technology German University In Cairo Cairo11865 Egypt Faculty of Computer and Information Sciences Ain Shams University Cairo11566 Egypt

In this paper, we propose a numerical spatiotemporal approach for video summarization. The current solutions leverage deep learning techniques to tackle this task. However, existing methods do not employ the video shots’ length data in their networks. We first introduce a new ground truth labelling for video summarization. This ground truth tackles multiple users’ annotations and is inclusive of video shot length information. We then propose a novel network architecture Numerical SpatioTemporal Fusion Net, NSTFNet. The proposed architecture leverages the temporal modelling ability of the self-attention mechanism to model video’s vision data to be fused with structured numerical features of video shots. We evaluate our results on TVSum and SumMe datasets. Experimental results show that the proposed model outperforms state-of-the-art performance on the SumMe dataset with 51.29% and 54.42% f-scores on the canonical and augmented configurations, demonstrating the effectiveness of our proposed model compared to state-of-the-art methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2025.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Diffusion Models Meet Network Management: Improving Traffic Matrix Analysis with Diffusion-Based Approach

引用

IEEE Transactions on Network and Service Management 2025年第2期22卷 1259-1275页

作者： Yuan, Xinyu Qiao, Yan Wei, Zhenchun Zhang, Zeyu Li, Minyue Zhao, Pei Hu, Rongyao Li, Wenjing Hefei University of Technology School of Computer Science and Information Engineering China Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology China Macau University of Science and Technology Faculty of Information Technology China

Due to network operation and maintenance relying heavily on network traffic monitoring, traffic matrix analysis has been one of the most crucial issues for network management related tasks. However, it is challenging to reliably obtain the precise measurement in computer networks because of the high measurement cost, and the unavoidable transmission loss. Although some methods proposed in recent years allowed estimating network traffic from partial flow-level or link-level measurements, they often perform poorly for traffic matrix estimation nowadays. Despite strong assumptions like low-rank structure and the prior distribution, existing techniques are usually task-specific and tend to be significantly worse as modern network communication is extremely complicated and dynamic. To address the dilemma, this paper proposed a diffusion-based traffic matrix analysis framework named Diffusion-TM, which leverages problem-agnostic diffusion to notably elevate the estimation performance in both traffic distribution and accuracy. The novel framework not only takes advantage of the powerful generative ability of diffusion models to produce realistic network traffic, but also leverages the denoising process to unbiasedly estimate all end-to-end traffic in a plug-and-play manner under theoretical guarantee. Moreover, taking into account that compiling an intact traffic dataset is usually infeasible, we also propose a two-stage training scheme to make our framework be insensitive to missing values in the dataset. With extensive experiments with real-world datasets, we illustrate the effectiveness of Diffusion-TM on several tasks. Moreover, the results also demonstrate that our method can obtain promising results even with 5% known values left in the datasets. © 2004-2012 IEEE.

关键词： Level measurement

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：