A Survey on Edge Computing (EC) Security Challenges: Classification, Threats, and Mitigation Strategies DOI Creative Commons
Abdul Manan Sheikh, Md. Rafiqul Islam, Mohamed Hadi Habaebi

и другие.

Future Internet, Год журнала: 2025, Номер 17(4), С. 175 - 175

Опубликована: Апрель 16, 2025

Edge computing (EC) is a distributed approach to processing data at the network edge, either by device or local server, instead of centralized centers cloud. EC proximity source can provide faster insights, response time, and bandwidth utilization. However, architecture makes it vulnerable security breaches diverse attack vectors. The edge paradigm has limited availability resources like memory battery power. Also, heterogeneous nature hardware, communication protocols, difficulty in timely updating patches exist. A significant number researchers have presented countermeasures for detection mitigation threats an paradigm. that differs from traditional privacy-preserving mechanisms already used cloud required. Artificial Intelligence (AI) greatly improves through advanced threat detection, automated responses, optimized resource management. When combined with Physical Unclonable Functions (PUFs), AI further strengthens leveraging PUFs’ unique unclonable attributes alongside AI’s adaptive efficient management features. This paper investigates various strategies cutting-edge solutions. It presents comparison between existing strategies, highlighting their benefits limitations. Additionally, offers detailed discussion threats, including characteristics classification different types. also provides overview privacy needs EC, detailing technological methods employed address threats. Its goal assist future pinpointing potential research opportunities.

Язык: Английский

Synchronization, Optimization, and Adaptation of Machine Learning Techniques for Computer Vision in Cyber-Physical Systems: A Comprehensive Analysis DOI Open Access

Kai Hung Tank,

Mohamed Chahine Ghanem, Vassil Vassilev

и другие.

Опубликована: Янв. 7, 2025

Cyber-Physical Systems (CPS) seamlessly integrate computers, networks, and physical devices, enabling machines to communicate, process data, respond real-world conditions in real-time. By bridging the digital worlds, CPS ensures operations that are efficient, safe, innovative, controllable. As smart cities autonomous become more prevalent, understanding is crucial for driving future progress. Recent advancements edge computing, AI-driven vision, collaborative systems have significantly enhanced capabilities. Synchronization, optimization, adaptation intricate processes impact performance across different domains. Therefore, identifying emerging trends uncovering research gaps essential highlight areas require further investigation improvement. A systematic review facilitates this by allowing researchers benchmark compare various techniques, evaluate their effectiveness, establish best practices. It provides evidence-based insights into optimal strategies implementation while addressing potential trade-offs performance, resource usage, reliability. Additionally, such reviews help identify widely accepted standards frameworks, contributing development of standardized approaches.

Язык: Английский

Процитировано

0
Edge AI Deploying Artificial Intelligence Models on Edge Devices for Real-Time Analytics DOI Creative Commons
Sagar Choudhary,

S Vijitha,

Dokku Durga Bhavani

и другие.

ITM Web of Conferences, Год журнала: 2025, Номер 76, С. 01009 - 01009

Опубликована: Янв. 1, 2025

Because of its on-the-go nature, edge AI has gained popularity, allowing for realtime analytics by deploying artificial intelligence models onto devices. Despite the promise Edge evidenced existing research, there are still significant barriers to widespread adoption with issues such as scalability, energy efficiency, security, and reduced model explainability representing common challenges. Hence, while this paper solves in a number ways, real use case deployment, modular adaptability, dynamic specialization. Our paradigm achieves low latency, better security efficiency using light-weight models, federated learning, Explainable (XAI) smart edge-cloud orchestration. This framework could enable generic beyond specific applications that depend on multi-modal data processing, which contributes generalization across various industries healthcare, autonomous systems, cities, cybersecurity. Moreover, work will help deploy sustainable employing green computing techniques detect anomalies near real-time critical domains helping ease challenges modern world.

Язык: Английский

Процитировано

0
Dense-stream YOLOv8n: a lightweight framework for real-time crowd monitoring in smart libraries DOI Creative Commons
Zhihao Chen, Jun Xu, Taorong Qiu

и другие.

Scientific Reports, Год журнала: 2025, Номер 15(1)

Опубликована: Апрель 4, 2025

Crowd monitoring in the context of smart libraries is great significance for resource optimization and service improvement. However, existing models struggle to achieve real-time performance accuracy high-density, enclosed environments.This study addresses these limitations following way: Firstly, pedestrian flow videos from side view angle were collected at different time periods on second floor library. The frame-extracted into images manually annotated, resulting a high-quality dataset consisting 5350 (3745 training set, 1070 test 535 validation set). Then, lightweight convolutional data augmentation module DensityNet was designed enhance model's feature extraction ability crowded occluded scenes. Subsequently, model pruning knowledge distillation techniques combined reduce complexity detection, making it suitable computing requirements edge devices. Finally, region detection algorithm better adapt demand crowd high-density limited dynamic environments by extending trigger time, providing an accurate contactless solution libraries. experimental results show that improved YOLOv8n has average scenes? [email protected] ?Reaching 0.99, close 0.991 original model, while At 0.95, reached 0.861, increase 0.014 compared before pruning; In terms performance, frame rate (FPS) significantly increased 254, computational load decreased 4.0 GFLOP, parameter count been reduced 2.04M, meeting needs peak proposed this research institute can be integrated intelligent library management system efficient optimization.

Язык: Английский

Процитировано

0
Performance Analysis of AI-Driven Security Models in the Cloud-Edge Continuum for Monitoring Critical Infrastructures DOI

Maitham Al-rubaye,

Atakan Aral

Lecture notes on data engineering and communications technologies, Год журнала: 2025, Номер unknown, С. 273 - 283

Опубликована: Янв. 1, 2025

Язык: Английский

Процитировано

0
A Survey on Edge Computing (EC) Security Challenges: Classification, Threats, and Mitigation Strategies DOI Creative Commons
Abdul Manan Sheikh, Md. Rafiqul Islam, Mohamed Hadi Habaebi

и другие.

Future Internet, Год журнала: 2025, Номер 17(4), С. 175 - 175

Опубликована: Апрель 16, 2025

Edge computing (EC) is a distributed approach to processing data at the network edge, either by device or local server, instead of centralized centers cloud. EC proximity source can provide faster insights, response time, and bandwidth utilization. However, architecture makes it vulnerable security breaches diverse attack vectors. The edge paradigm has limited availability resources like memory battery power. Also, heterogeneous nature hardware, communication protocols, difficulty in timely updating patches exist. A significant number researchers have presented countermeasures for detection mitigation threats an paradigm. that differs from traditional privacy-preserving mechanisms already used cloud required. Artificial Intelligence (AI) greatly improves through advanced threat detection, automated responses, optimized resource management. When combined with Physical Unclonable Functions (PUFs), AI further strengthens leveraging PUFs’ unique unclonable attributes alongside AI’s adaptive efficient management features. This paper investigates various strategies cutting-edge solutions. It presents comparison between existing strategies, highlighting their benefits limitations. Additionally, offers detailed discussion threats, including characteristics classification different types. also provides overview privacy needs EC, detailing technological methods employed address threats. Its goal assist future pinpointing potential research opportunities.

Язык: Английский

Процитировано

0