检索结果-内蒙古大学图书馆

Privacy protection and data security in intelligent recommendation systems

Neural Computing and Applications 2025年 1-18页

作者： Zheng, Donghua Alkawaz, Mohammed Hazim Johar, Md Gapar Md School of Information Technology and Engineering Guangzhou College of Commerce Guangdong Guangzhou511363 China School of Graduate Studies Management and Science University Selangor Shah Alam40100 Malaysia Department of Computer Science College of Education for Pure Science University of Mosul Nineveh Mosul41002 Iraq Software Engineering and Digital Innovation Centre Management and Science University Selangor Shah Alam40100 Malaysia

Data security and privacy have emerged as major areas of study for recommendation systems. This is crucial for enhancing system security given the quick advancement of Internet technology and its increased use. However, there are still issues with privacy protection and data security in current intelligent recommendation systems, such as a high probability of privacy leakage, low data security, and poor recommendation performance. To better promote the wider application of intelligent recommendation systems, this article introduces federated learning and differential privacy technology to conduct in-depth research on privacy protection and data security in intelligent recommendation systems. In the article, a federated learning framework is used to construct an intelligent recommendation system model, and the constructed model is trained. Furthermore, a differential privacy mechanism is introduced, which can protect the privacy of samples by analyzing the sensitivity of L1 and L2, gradient descent, gradient pruning, and other methods. Next, the secure multi-party computation (SMC) protocol can be used to achieve model parameter sharing and protect the privacy of participants;subsequently, there is the implementation of federated learning. Finally, this article also evaluates the practical application effects of federated learning and differential privacy technology in privacy protection and data security in intelligent recommendation systems. The study’s findings indicate that the approach suggested in this article has an average data security and privacy leakage risk of 5.35% and 96.64%;federated learning is 16.55% and 85.08%, respectively;differential privacy is 9.65% and 88.47%, respectively;deep learning is 21.08% and 77.92%, respectively;and homomorphic encryption is 10.69% and 82.43%, respectively. The combination of federal learning and differential privacy can effectively protect the privacy and data security of the intelligent recommendation system, reduce

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Evaluating Feature Prioritization in a Reduced Feature Set Using Explainable AI for Intracranial Aneurysm Classification

Evaluating Feature Prioritization in a Reduced Feature Set U...

引用

International Conference on Advancements in Computational sciences (ICACS)

作者： Iram Abdullah Ali Javed Department of Computer Science Air University Kamra Pakistan Department of Software Engineering University of Engineering & Technology Taxila Pakistan

ISBN: (数字)9798331533038

ISBN: (纸本)9798331533045

The timely management of an unruptured aneurysm can prevent hemorrhage. Multiple anatomical, morphological, and hemodynamic features associated with an aneurysm can predict the risk of rupture and classify the nature of the aneurysm as either ruptured or unruptured. However, considering all features may create ambiguities in the model due to inter-dependencies, such as the correlation between aneurysm height and width to aneurysm area. In computer-aided medical diagnostics, focusing on relevant features that diagnose the disease is more crucial than using an abundance of features that may not contribute to the diagnosis and may cause unnecessary complexity. The use of independent or sparsely correlated features improves the accuracy of the classifier. The proposed research analyzes the interdependency of features by calculating the correlation between features. Based on the analyses, the high correlation threshold is determined through rigorous experimentation. From the highly correlated features, one feature is selected. Consequently, the reduced feature set is recommended. The reduced feature set performs better with simpler classifiers. Instead of choosing a classifier that struggles with a broad range of features, an appropriately optimized feature set can enhance performance and improve accuracy. The proposed approach is tested on a publicly available dataset of aneurysms, leading to an improvement in classification accuracy from 82.6% to 87%, due to the use of an appropriate feature set. Moreover, the best model was evaluated using two different explainable AI frameworks to assess the contribution of each feature in prediction. However, the conflicting feature prioritization in each explainable framework suggests that these models prioritize different features for the same trained model, leading to ambiguity. This inconsistency indicates that the explainable models lack generalization and fail to consistently analyze feature importance.

关键词： Accuracy Correlation Explainable AI Computational modeling Redundancy Training data Aneurysm Predictive models Medical diagnosis Random forests

来源：评论

学校读者我要写书评

暂无评论

"i look like a gorilla, but don't move like one!": Impact of Avatar-Locomotion Congruence in Virtual Reality

"i look like a gorilla, but don't move like one!": Impact of...

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Khan, Omar Nam, Hyeongil Kim, Kangsoo University of Calgary Department of Computer Science Canada University of Calgary Department of Electrical and Software Engineering Canada

ISBN: (纸本)9798331514846

As virtual reality (VR) continues to expand, particularly in social VR platforms and immersive gaming, understanding the factors that shape user experience is becoming increasingly important. Avatars and locomotion methods play central roles in influencing how users identify with their virtual representations and navigate virtual spaces. However, little is known about the impact of congruence between these two factors. We conducted a user study with 30 participants, employing two avatar types (human and gorilla) and two locomotion methods (human-like arm-swing and gorilla-like arm-roll), to assess the effects of avatar-locomotion congruence. Our results indicate that congruent avatar-locomotion conditions enhance avatar identification and user experience. © 2025 IEEE.

关键词： appearance avatar identification avatars gamification locomotion usability user experience Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Ownership Verification for Federated Recommendation

引用

ACM Transactions on Information Systems 2025年第3期43卷 1-27页

作者： Enyue Yang Weike Pan Lixin Fan Hanlin Gu Zhitao Li Qiang Yang Zhong Ming College of Computer Science and Software Engineering Shenzhen University Shenzhen China AI Department WeBank Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong China and AI Department WeBank Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Technology University Shenzhen China and Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ) Shenzhen China

Most federated learning-based recommender systems allow clients to access a well-trained high-quality model locally, which provides adversaries with the opportunity to infringe the legitimate copyright of the model. In response, we study an emerging and important problem, i.e., copyright protection of a federated recommendation model, which has not yet been addressed in the community of federated learning or recommender systems. We propose the first backdoor-based ownership verification scheme for federated recommendation (OVFR), which enables the server to claim its ownership for a given suspicious recommendation model. First, we propose to generate a trigger set tailored to recommendation scenarios. In particular, we generate some fake users and items, and then construct a set of fake users with fake interaction records as a trigger set. Moreover, we ensure that the distribution of the popularity of the fake items follows a long-tailed distribution for the effectiveness of the incorporated watermarking. To provide robustness assurance, we propose two different hybrid strategies to make the embeddings of the fake items similar to those of the real items. Second, we focus on effectively learning from a trigger set for recommendation scenarios. In particular, we design an MSE loss function and a contrastive loss function for incorporating the backdoor-based watermarking into the item embeddings, since the item embeddings are often more valuable and easier to be accessed than other parameters of a federated recommendation model. We then design a contrastive loss function to reduce the risk of the fake items being detected. Extensive experiments on three public datasets show the effectiveness of our OVFR in terms of ownership verification, model performance, and robustness.

关键词： Federated recommendation Ownership verification

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach Using Machine Learning for Accurate Detection of DDoS Attack in software Defined Network 2nd

A Novel Approach Using Machine Learning for Accurate Detecti...

引用

2nd International Conference on Cyber Intelligence and Information Retrieval, CIIR 2023

作者： Sharma, Hitesh Kumar Choudhury, Tanupriya Kotecha, Ketan Mahdi, Hussain Falih Dutta, Soumi Bhattacharya, Abhishek Sar, Ayan Energy Acres Bidholi Uttarakhand Bidholi India School of Computer Science University of Petroleum and Energy Studies Uttarakhand Dehradun India Pune India Pune India Department of Computer and Software Engineering University of Diyala Baquba Iraq Sister Nivedita University Chakpachuria India

ISBN: (纸本)9789819776023

A denial Of Service (DoS) attack is termed an attack when the request-receiving server or network shuts down or becomes inaccessible for service. This kind of attack is caused by flooding the target server or network with huge traffic or sending information which can trigger a vulnerability to the server and lead to server crash. Different kinds of DoS attacks can occur on a network including a classic DoS attack which is carried out by a single client machine sending tons of requests and data to a server by itself to increase its processing to the extent that no new genuine requests are answered by the server and network is ultimately unreachable. Another kind of DoS attack is termed a DDoS (Distributed Denial Of Service) attack which includes a master host machine that leverages the network of machines around it to send multiple requests to the server from different machines which act as zombie machines for the attack as the machine won’t even have an idea itself that they are being used for an attack on the server. As multiple requests and data hits the server from different locations, the server becomes unavailable for processing and leads to network failure. These zombie machines are termed botnets which are connected online and are used to overwhelm a target website with fake traffic. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Denial-of-service attack

来源：评论

学校读者我要写书评

暂无评论

Decentralized Authentication Scheme Incorporating Reputation and Attribute Signature for Cross-Web3 Applications

引用

IEEE Internet of Things Journal 2025年第10期12卷 14526-14537页

作者： Song, Xiaoling Xu, Guangxia Huang, Yongfei Liu, Yong Chongqing University of Posts and Telecommunications School of Computer Science and Technology Chongqing400065 China Guangzhou University Cyberspace Institute of Advanced Technology Guangzhou510006 China Peng Cheng Laboratory Department of New Networks Shenzhen518000 China Chongqing University of Posts and Telecommunications School of Software Engineering Chongqing400065 China

Driven by Web 3.0, the number of decentralized applications (DAPPs) continues to increase, and the need for decentralized authentication across applications becomes more and more significant. In addition, multi-dimensional reputation assessment becomes especially critical in a decentralized environment. However, there is still a lack of trusted and flexible self-sovereign identity (SSI) authentication mechanisms in Web 3.0 decentralized zero-trust cross-applications access scenarios. In response to these challenges, we propose a decentralized authentication scheme that fuses reputation assessment and attribute signature for the open and self-organized Web3 application. Firstly, we design an attribute signature method based on the attributes in a user's verifiable credentials (VCs). The signature can be used for authentication across Web3 applications, and the authenticator can flexibly adjust the attributes to be verified and their number according to specific needs. Meanwhile, in the attribute signature, we construct a multi-dimensional reputation assessment mechanism to comprehensively assess the user's reputation from multiple aspects to determine his/her security risk level, so as to reduce the possibility of identity fraud. Ultimately, through comparative analysis, we verify the advantages of the scheme in terms of privacy, scalability and attack resistance. Moreover, we analyze the performance of the key algorithms in the scheme through simulation experiments, and the experimental results show that our scheme is feasible. © 2014 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

Medical Image Classification with KAN-Integrated Transformers and Dilated Neighborhood Attention

arXiv

引用

arXiv 2025年

作者： Manzari, Omid Nejati Asgariandehkordi, Hojat Koleilat, Taha Xiao, Yiming Rivaz, Hassan Tehran Iran Department of Electrical and Computer Engineering Concordia University Montreal Canada Department of Computer Science and Software Engineering Concordia University Montreal Canada

Convolutional networks, transformers, hybrid models, and Mamba-based architectures have demonstrated strong performance across various medical image classification tasks. However, these methods were primarily designed to classify clean images using labeled data. In contrast, real-world clinical data often involve image corruptions that are unique to multi-center studies and stem from variations in imaging equipment across manufacturers. In this paper, we introduce the Medical Vision Transformer (MedViTV2), a novel architecture incorporating Kolmogorov-Arnold Network (KAN) layers into the transformer architecture for the first time, aiming for generalized medical image classification. We have developed an efficient KAN block to reduce computational load while enhancing the accuracy of the original MedViT. Additionally, to counteract the fragility of our MedViT when scaled up, we propose an enhanced Dilated Neighborhood Attention (DiNA), an adaptation of the efficient fused dot-product attention kernel capable of capturing global context and expanding receptive fields to scale the model effectively and addressing feature collapse issues. Moreover, a hierarchical hybrid strategy is introduced to stack our Local Feature Perception and Global Feature Perception blocks in an efficient manner, which balances local and global feature perceptions to boost performance. Extensive experiments on 17 medical image classification datasets and 12 corrupted medical image datasets demonstrate that MedViTV2 achieved state-of-the-art results in 27 out of 29 experiments with reduced computational complexity. MedViTV2 is 44% more computationally efficient than the previous version and significantly enhances accuracy, achieving improvements of 4.6% on MedMNIST, 5.8% on NonMNIST, and 13.4% on the MedMNIST-C benchmark. Our code is available at https://***/Omid-Nejati/*** © 2025, CC BY.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

A Red/Blue Video Game for Hide&Seek Analysis for Hardware Trojans and the Seeker's Dilemma

A Red/Blue Video Game for Hide&Seek Analysis for Hardware Tr...

引用

Annual IEEE Systems Conference

作者： Peter Jamieson Obed Amaning-Yeboah Jared Butler Deniz Misirlioglu Riley Taylor Suman Bhunia Department of Electrical and Computer Engineering Miami University Oxford Ohio USA Department of Computer Science and Software Engineering Miami University Oxford Ohio USA

ISBN: (数字)9798331508180

ISBN: (纸本)9798331508197

This paper describes our work in creating a video game to analyze the human dynamics of a Hide&Seek game. By harnessing human computation, we use this approach to get insights into how humans in a game Hide&Seek help understand how this relates to other problems, such as how Hardware Trojans might be hidden in an Integrated Chip. Hide&Seek can be directly related to cybersecurity, and in recent work, this idea has been extended further for hardware trojans in the perspective of The Seeker's Dilemma (an extension of Hide&Seek on a graph). Within the cybersecurity context, Hide&Seek is analogous to a continuous game of cat-and-mouse: the red player (the cat) assumes the role of the seeker, while the blue player (the mouse) acts as the hider. This study aims to model these games with human players and mathematical representations of Hide&Seek on a graph to collect data to better understand the hiding and seeking problems for a given graph. We describe the video game and provide results for a small sample of players hiding and seeking on three levels/graphs.

关键词： Video games Aggregates Games Data collection Hardware Mathematical models Data models Trojan horses computer security

来源：评论

学校读者我要写书评

暂无评论

Tropical Cyclone Intensity Prediction Using Spatio-Temporal Data Fusion

引用

IEEE Access 2025年 13卷 70095-70104页

作者： Sattar, Kalim Muhammad Saad Missen, Malik Saher, Najia Nawaz Bashir, Rab Zoupash Zahra, Syeda Faheem, Muhammad Rehman Khan, Amjad Department of Information Technology Islamia University of Bahawalpur Bahawalpur63100 Pakistan Department of Software Engineering Islamia University of Bahawalpur Bahawalpur63100 Pakistan Department of Artificial Intelligence Islamia University of Bahawalpur Bahawalpur63100 Pakistan COMSATS University Islamabad Department of Computer Science Vehari Campus Vehari61100 Pakistan Riyadh12435 Saudi Arabia VTT Technical Research Centre of Finland Espoo02150 Finland

Tropical cyclone is a sea storm that causes important life and economic losses in the coastal regions in the tropical zone around the equator of the earth. Tropical cyclone intensity is an important characteristic used to estimate the strength of the tropical cyclone. This study aims to improve the tropical cyclone intensity prediction by concatenating the spatial and temporal features of tropical cyclones. The proposed methodology utilized the deep learning based approach for handling 3D and 2D features for 24h early intensity prediction. In the first phase, a dynamic grid-based approach is utilized to extract the spatial features in a ( 3 × 3 ) grid format from the eye of the TC. These spatial features are extracted for four different components (u,v,t,r) and 37 different isobaric planes. In the second step, multiple convolutional layers are used to process each spatial component separately, and a fusion method is used to combine the spatial and temporal features. The proposed method achieved state-of-the-art results by reducing the MAE up to 3.31% overall and 8.5%,14.78%, 5.67% for u,v, and (u,v) add fusion components, respectively. The proposed methodology outperformed the state-of-the-art Saf-net model by 8.5 %,14.78%,5.67% for u,v, and (u,v) add fusion, respectively. A performance comparison on four real-time tropical cyclones (Bavi 2015, AERE 2016, NANMADOL 2017, HECTOR 2018) is also performed. The proposed model achieved MAE 2.92, 2.99, 2.46, 3.95 that are 10.08%, 34.35%, 23.65%, and 3.2% lower than state-of-the-art spatio-temporal models, respectively. © 2013 IEEE.

关键词： Tropical cyclone

来源：评论

学校读者我要写书评

暂无评论

Breaking the Vault: A Case Study of the 2022 LastPass Data Breach

arXiv

引用

arXiv 2025年

作者： Gentles, Jessica Fields, Mason Goodman, Garrett Bhunia, Suman Department of Computer Science and Software Engineering Miami University OxfordOH45056 United States

Managing the security of employee work computers has become increasingly important as today’s work model shifts to remote and hybrid work plans. In this paper, we explore the recent 2022 LastPass data breach, in which the attacker obtained sensitive customer data by exploiting a software vulnerability on a DevSecOps engineer’s computer. We discuss the methodology of the attacker as well as the impact this incident had on LastPass and its customers. Next, we expand upon the impact the breach had on LastPass as well as its customers. From this, we propose solutions for preparing for and mitigating similar attacks in the future. The aim of this paper is to shed light on the LastPass incident and provide methods for companies to secure their employee base, both nationally and internationally. With a strong security structure, companies can vastly reduce the chances of falling victim to a similar attack. © 2025, CC BY.

关键词： Cloud security

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：