检索结果-内蒙古大学图书馆

Electrical, Electronics, Information and Communication Technologies (ICEEICT), International Conference on

作者： Aditya G Kulkarni Prajwalasimha S N Naveen Kulkarni Deepthika Karuppusamy Raveena Dharmappa Yash Bagga Department of Computer Science and Engineering (Cyber Security) School of Engineering (SoE) Dayananda Sagar University Bangalore India

ISBN: (数字)9798350369083

ISBN: (纸本)9798350369090

In order to fortify pre-stored biometric data of fingerprint samples in the biometric authentication system, a hybrid approach based on Pseudo Hadamard transformation and Skew Tent chaotic substitution is proposed. Inter pixel redundancy and strong correlation between the adjacent pixels in an image is condensed by imperiling it to transformation and chaotic substitution. Pixel value variation is accomplished using modified Pseudo Hadamard chaotic transformation and pixel position variation is made by substitution using S-boxes. Secrete key is used for encryption with 256 bits. S-box is constructed using chaotic Skew Tent map to generate random numbers. Fingerprint images are considered from FVC2004. Encrypted/Decrypted images are considered for experimental analysis. Two stage fortifications are provided using transformation and substitution. The results obtained for standard images are compared to existing techniques and high degree of security is achieved by this proposed technique.

关键词： Correlation Chaotic communication Image matching Redundancy Fingerprint recognition Matrices Encryption Information and communication technology Standards Random sequences

来源：评论

学校读者我要写书评

暂无评论

PPO-Based Mobile Robot Path Planning with Dense Bootstrap Reward in Partially Observable Environments

PPO-Based Mobile Robot Path Planning with Dense Bootstrap Re...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Zhou Shujie School of Computer Science and Engineering (School of Cyber Security) University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

Path planning in large, complex environments poses significant challenges, as a single robot must efficiently navigate to its target while avoiding obstacles. Traditional algorithms often struggle to balance computational efficiency and planning accuracy. Reinforcement learning methods, while promising, frequently suffer from convergence issues due to difficult-to-tune hyperparameters and sparse reward signals. This paper introduces a Proximal Policy Optimization (PPO)-based path planning approach with a dense bootstrap reward mechanism. The proposed method enhances learning efficiency and ensures smooth navigation by incorporating a structured reward design, significantly improving the agent's path-planning performance in complex scenarios. We conducted simulation experiments in a classical warehouse environment to demonstrate the effectiveness and superiority of our proposed method. Compared to traditional rewards, our method significantly improves the pathfinding efficiency of deep reinforcement learning algorithms.

关键词： Navigation Information processing Media Deep reinforcement learning Path planning Robustness Planning Mobile robots Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Threat Defence Mechanism Through Self Defending Network to Prevent Hijacking in WiFi Network

An Adaptive Threat Defence Mechanism Through Self Defending ...

引用

Advances in Electronics, Communication, Computing and Intelligent Information Systems (ICAECIS), International Conference on

作者： Datta Sai Manikanta Narayana Sai Bharadwaj Nookala Shraddha Chopra Udhayakumar Shanmugam Department of Computer Science and Engineering (Cyber Security) School of Computing Chennai

IEEE 802.11 generally known as the Wi-Fi network, is our backbone of the present communication system delivering the best effort service to the end users. Access control in wireless network is an intrinsic security problem which creates possibilities for malevolent manipulation by third parties. Hackers make the use of free software to easily execute wireless attacks to create denial of service (DOS) and man in the middle attack and thereby the existing defense becomes passive for new types of network attacks. The paper proposes a self-defending network that can quickly identify the attackers, prevent them from doing further damage and then get itself adapt to the threat behavior. To implement the mechanism a pre-connection attack is performed by targeting a network and analyzing the packets. The proposed work demonstrates how a hacker gains access to a Wi-Fi network by cracking different types of encryptions like Wired Equivalent Privacy (WEP), Wireless Protected Access (WPA)/WPA2 using a simple wireless network adapter. Our proposed adaptive threat defense model identifies the hacker and creates a diverse strategy for self-defense. The proposed model would be effective against dynamic network configuration like Wi-Fi and further prevents hijacking.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the security of Smart Home Systems:A Survey

引用

Journal of computer science & Technology 2023年第2期38卷 228-247页

作者：袁斌万俊吴宇晗邹德清金海 School of Cyber Science and Engineering Huazhong University of Science and TechnologyWuhan 430074China Hubei Key Laboratory of Distributed System Security Huazhong University of Science and Technology Wuhan 430074China Hubei Engineering Research Center on Big Data Security Huazhong University of Science and Technology Wuhan 430074China National Engineering Research Center for Big Data Technology and System Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Lab Huazhong University of Science and TechnologyWuhan 430074China Shenzhen Huazhong University of Science and Technology Research Institute Shenzhen 518057China School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Lab Huazhong University of Science and TechnologyWuhan 430074China

Among the plethora of IoT(Internet of Things)applications,the smart home is one of the ***,the rapid development of the smart home has also made smart home systems a target for ***,researchers have made many efforts to investigate and enhance the security of smart home *** a more secure smart home ecosystem,we present a detailed literature review on the security of smart home ***,we categorize smart home systems’security issues into the platform,device,and communication *** exploring the research and specific issues in each of these security areas,we summarize the root causes of the security flaws in today's smart home systems,which include the heterogeneity of internal components of the systems,vendors'customization,the lack of clear responsibility boundaries and the absence of standard security ***,to better understand the security of smart home systems and potentially provide better protection for smart home systems,we propose research directions,including automated vulnerability mining,vigorous security checking,and data-driven security analysis.

关键词： IoT(Internet of Things) smart home IoT security smart home security

来源：评论

学校读者我要写书评

暂无评论

Dynamic Graph-Enhanced Sequential LSTM for Context-Aware Point-of-Interest Recommendation

Dynamic Graph-Enhanced Sequential LSTM for Context-Aware Poi...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： Zhang Yuwen Ren Shaobo School of Computer Science and Engineering (School of Cyber Security) University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

Next Point-of-Interest (POI) recommendation is a critical task in location-based services, aiming to predict the user's next POI based on historical check-in data. Existing approaches often rely on static graphs or sequential models to capture user preferences, which are limited by the sparsity of check-in data and the inability to dynamically model spatio-temporal transitions. To address these challenges, we propose the Dynamic Graph-Enhanced LSTM (DGEL) model for next POI recommendation. DGEL constructs dynamic POI transition graphs by combining Transformer-based graph learning with embedding techniques, capturing implicit relationships between POIs. Additionally, a Customized Sequential LSTM (CS-LSTM) is introduced to model long-term and short-term dependencies, incorporating spatial, temporal, and relational signals. Experimental results on Gowalla and Foursquare datasets demonstrate that DGEL achieves significant performance improvements over state-of-the-art baselines, highlighting its effectiveness in leveraging dynamic graphs and structured sequential learning for POI recommendation.

关键词： Computational modeling Neural networks Information processing Media Transformers Data models Long short term memory Context modeling

来源：评论

学校读者我要写书评

暂无评论

Sine Cosine Reptile Search Algorithm with Grid Search Support Vector Machine based Ransomware Detection and Classification 2

Sine Cosine Reptile Search Algorithm with Grid Search Suppor...

引用

2nd IEEE International Conference on Integrated Circuits and Communication Systems, ICICACS 2024

作者： Adnan, Myasar Mundher Devi, S. Vaag Deepthi, V.S. Raghunathareddy, M.V. Yamsani, Nagendar The Islamic University Najaf Iraq City Engineering College Department of Artificial Intelligence and Machine Learning Karnataka Bangalore India Cyber Security Dayananda Sagar College of Engineering Department of Computer Science and Engineering Karnataka Bangalore India Nitte Meenakshi Institute of Technology Department of Electronics and Communication Engineering Bengaluru India SR University School of Computer Science and Artificial Intelligence Warangal India

ISBN: (纸本)9798350317558

The ransomware exploits the system data and takes off the significant information of the user without any intimation. Moreover, the ransomware furtively directs that information to the servers which are organized by the attackers. In recent years, many researchers and scientists discovered anti-malware products to identify known malware. But these methods are not robust to detect complicated and packed malware. To overcome these problems, the Sine Cosine Reptile Search Algorithm with Grid Search Support Vector Machine (SCRSA-GSSVM) is proposed for ransomware detection and classification. The Drebin dataset is employed in this paper and min-max standardization is utilized aimed at preprocessing. The SCRSA is utilized for feature selection and GSSVM is utilized for classification. The SVM is tuned by GS which reduces the noise and false positives to enhance the model performance. Performance of SCRSA-GSSVM is assessed with presentation measure of accuracy, precision, recall and f1-score. The SCRSA-GSSVM attains 99.85% accuracy, 99.83% precision, 99.83% recall and 99.78% f1-score which is better when compared to Random Forest (RF) and Artificial Neural Network (ANN). © 2024 IEEE.

关键词： +Support Vector Machine Grid Search Min-max Normalization Ransomware Reptile Search Algorithm

来源：评论

学校读者我要写书评

暂无评论

FEDA: Private-Preserving Data Aggregation for Smart Grid via Functional Encryption

FEDA: Private-Preserving Data Aggregation for Smart Grid via...

引用

International Conference on Wavelet Active Media Technology and Information Processing (ICWAMTIP)

作者： LI ZHENJIANG LI HONGWEI QIAN XINYUAN School of Computer Science and Engineering (School of Cyber Security) University of Electronic Science and Technology of China Chengdu China

ISBN: (数字)9798331519254

ISBN: (纸本)9798331519261

Privacy-preserving data aggregation (P2DA) is a technique that enables the simultaneous availability of data and the preservation of privacy in smart grid systems. However, existing methods are only capable of fulfilling a subset of the essential criteria for the development of smart grids. The current methodologies are based on a number of strong assumptions, or else they result in an increase in the computational and communication overhead. To address this challenge, this paper introduces FEDA, a P2DA scheme based on functional encryption for smart grids, offering efficient encryption and decryption processes, along with verifiable aggregation. The results of our experiments demonstrate that our approach markedly reduces the computational and communication overheads in comparison to existing methods. Furthermore, it enhances the encryption speed by approximately eightfold and improves the aggregation and decryption efficiencies while maintaining a high level of security.

关键词： Privacy Fault tolerance Data privacy Fault tolerant systems Information processing Data aggregation Media Encryption Smart grids security

来源：评论

学校读者我要写书评

暂无评论

Universal Watermark Vaccine: Universal Adversarial Perturbations for Watermark Protection

Universal Watermark Vaccine: Universal Adversarial Perturbat...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Chen, Jianbo Liu, Xinwei Liang, Siyuan Jia, Xiaojun Xun, Yuan Hunan University College of Computer Science and Electronic Engineering Hunan China Chinese Academy of Sciences Institute of Information Engineering Beijing China University of Chinese Academy of Sciences School of Cyber Security Beijing China

ISBN: (纸本)9798350302493

As computing ability continues to rapidly develop, neural networks have found widespread use in various fields. However, in the realm of visible watermarking for image copyright protection, neural networks have made image protection through watermarking less effective. Some research has even shown that watermarks can be removed without damaging to the original image, posing a significant threat to digital copyright protection. In response, the community has introduced adversarial perturbations for watermark protection, but these are sample-specific and time-consuming in real-world scenarios. To address this issue, we propose a new universal adversarial perturbation for watermark removal networks that offers two options. The first option involves adding perturbations to the entire host image, bringing the output of the watermark removal network closer to the original image and providing protection. The second option involves adding perturbations only to the watermark position, reducing the impact of the perturbation on the image and enhancing stealthiness. Our experiments demonstrate that our method effectively resists watermark removal networks and has good generalizability across different images. © 2023 IEEE.

关键词： Copyrights

来源：评论

学校读者我要写书评

暂无评论

Multi-Behavioral Recommender System with Heterogeneous Graph Learning

Multi-Behavioral Recommender System with Heterogeneous Graph...

引用

Consumer Electronics and computer engineering (ICCECE), 2021 IEEE International Conference on

作者： Jiaming Feng Yang Liu Junjie Zhang School of Computer Science and Engineering (School of Cyber Security) University of Electronic Science and Technology of China Chengdu China

With the rapid development of online platforms and the explosive growth of user-generated data, personalized recommendation systems have become increasingly crucial in delivering relevant content to users. Traditional recommendation approaches often focus on modeling user-item interactions, neglecting the rich contextual information associated with user behaviors. In this paper, we propose a novel multi-behavior recommendation system based on heterogeneous graph learning. By leveraging the power of heterogeneity, our model integrates various types of user behaviors, such as browsing, adding cart, and purchasing, into a unified framework. We design a graph-based representation for capturing the complex relationships between users, items, and behaviors. Additionally, we introduce a graph neural network approach to effectively propagate and aggregate information across the heterogeneous graph. Experimental results on a real-world dataset demonstrate that our proposed system outperforms state-of-the-art recommendation methods in terms of accuracy and diversity. The findings highlight the potential of heterogeneous graph learning in enhancing the performance of multi-behavior recommendation systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

BlockWhisper: A Blockchain-Based Hybrid Covert Communication Scheme with Strong Ability to Evade Detection 24th

BlockWhisper: A Blockchain-Based Hybrid Covert Communication...

引用

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

作者： Wu, Zehui Xu, Yuwei Huang, Ranfeng Fan, Xinhe Xu, Jingdong Cheng, Guang School of Cyber Science and Engineering Southeast University Nanjing China Purple Mountain Laboratories for Network and Communication Security Nanjing China Engineering Research Center of Blockchain Application Supervision and Management Nanjing China Software College Northeastern University Shenyang China College of Computer Science Nankai University Tianjin China

ISBN: (纸本)9789819615247

In light of the pervasive significance of privacy protection in contemporary society, the exploration of covert communication technology has been extensive, which is designed to safeguard communication behaviors and contents from disclosure. The decentralization, anonymity, and robustness of blockchain technology render it a more suitable medium for covert communication than traditional networks, which are vulnerable to tracing and destruction. Nevertheless, state-of-the-art blockchain-based covert communication schemes tend to focus on the concealment of a single type of constituent element in a blockchain transaction. These methods are able to resist detection methods for a particular element, yet are easily exposed under the joint detection of multiple classes of methods. The absence of resistance to joint detection methods targeting all elements presents a significant challenge that impedes the advancement of blockchain-based covert channels. Consequently, BlockWhisper is proposed as a blockchain-based hybrid covert channel that is capable of evading the recognition of various detection methods. Following the probability distribution model obtained from a blockchain transaction distribution analysis method, BlockWhisper is implemented using a top address list and a special hybrid coding method. The experiments demonstrated that Graph-based Detection (GD), Similarity-based Detection (SMD), Shape-based Detection (SPD), Entropy-based Detection (ETD), and Machine Learning-based Detection (MLD) yielded inferior results on this scheme, which substantiates the assertion that BlockWhisper possesses a strong ability to evade detection. Moreover, a comparison of BlockWhisper with other schemes reveals that it has a superior channel capacity on the basis of the guarantee of channel feasibility. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Blockchain Covert communication Evading detection

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：