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

et al.

Future Internet, Journal Year: 2025, Volume and Issue: 17(4), P. 175 - 175

Published: April 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.

Language: Английский

A Survey on Optimization Techniques for Edge Artificial Intelligence (AI) DOI Creative Commons

Chellammal Surianarayanan,

John Jeyasekaran Lawrence,

Pethuru Raj Chelliah

et al.

Sensors, Journal Year: 2023, Volume and Issue: 23(3), P. 1279 - 1279

Published: Jan. 22, 2023

Artificial Intelligence (Al) models are being produced and used to solve a variety of current future business technical problems. Therefore, AI model engineering processes, platforms, products acquiring special significance across industry verticals. For achieving deeper automation, the number data features while generating highly promising productive is numerous, hence resulting bulky. Such heavyweight consume lot computation, storage, networking, energy resources. On other side, increasingly, deployed in IoT devices ensure real-time knowledge discovery dissemination. Real-time insights paramount importance producing releasing intelligent services applications. Thus, edge intelligence through on-device processing has laid down stimulating foundation for enterprises environments. With these emerging requirements, focus turned towards unearthing competent cognitive techniques maximally compressing huge without sacrificing performance. researchers have come up with powerful optimization tools optimize models. This paper dig deep describe all kinds at different levels layers. Having learned methods, this work highlighted having an enabling framework.

Language: Английский

Citations

42
Federated Learning for IoT: A Survey of Techniques, Challenges, and Applications DOI Creative Commons
Ηλίας Δρίτσας, Μαρία Τρίγκα

Journal of Sensor and Actuator Networks, Journal Year: 2025, Volume and Issue: 14(1), P. 9 - 9

Published: Jan. 22, 2025

Federated Learning (FL) has emerged as a pivotal approach for decentralized Machine (ML), addressing the unique demands of Internet Things (IoT) environments where data privacy, bandwidth constraints, and device heterogeneity are paramount. This survey provides comprehensive overview FL, focusing on its integration with IoT. We delve into motivations behind adopting FL IoT, underlying techniques that facilitate this integration, challenges posed by IoT environments, diverse range applications is making an impact. Finally, submission also outlines future research directions open issues, aiming to provide detailed roadmap advancing in settings.

Language: Английский

Citations

2
A survey of multimodal hybrid deep learning for computer vision: Architectures, applications, trends, and challenges DOI
Khaled Bayoudh

Information Fusion, Journal Year: 2023, Volume and Issue: 105, P. 102217 - 102217

Published: Dec. 30, 2023

Language: Английский

Citations

32
Energy-Efficient Federated Learning With Resource Allocation for Green IoT Edge Intelligence in B5G DOI Creative Commons
Adeb Salh, Razali Ngah, Lukman Audah‏

et al.

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 16353 - 16367

Published: Jan. 1, 2023

An edge intelligence-aided Internet-of-Things (IoT) network has been proposed to accelerate the response of IoT services by deploying intelligence near devices. The transmission data from devices nodes leads large traffic in wireless connections. Federated Learning (FL) is solve high computational complexity training model locally on and sharing parameters nodes. This paper focuses developing an efficient integration joint depending investigating energy-efficient bandwidth allocation, computing Central Processing Unit (CPU) frequency, optimization power, desired level learning accuracy minimize energy consumption satisfy FL time requirement for all proposal efficiently optimized computation frequency allocation reduced solving problem closed form. remaining power loss could be resolved with Alternative Direction Algorithm (ADA) reduce at every iteration simulation results indicated that ADA can adapt central processing unit control cost a small growth time.

Language: Английский

Citations

26
Machine learning methods for service placement: a systematic review DOI Creative Commons
Parviz Keshavarz Haddadha, Mohammad Hossein Rezvani, Mahdi Mollamotalebi

et al.

Artificial Intelligence Review, Journal Year: 2024, Volume and Issue: 57(3)

Published: Feb. 17, 2024

Abstract With the growth of real-time and latency-sensitive applications in Internet Everything (IoE), service placement cannot rely on cloud computing alone. In response to this need, several paradigms, such as Mobile Edge Computing (MEC), Ultra-dense (UDEC), Fog (FC), have emerged. These paradigms aim bring resources closer end user, reducing delay wasted backhaul bandwidth. One major challenges these new is limitation edge dependencies between different parts. Some solutions, microservice architecture, allow parts an application be processed simultaneously. However, due ever-increasing number devices incoming tasks, problem solved today by relying rule-based deterministic solutions. a dynamic complex environment, many factors can influence solution. Optimization Machine Learning (ML) are two well-known tools that been used most for placement. Both methods typically use cost function. usually way define difference predicted actual value, while ML aims minimize simpler terms, gap prediction reality based historical data. Instead explicit rules, uses Due NP-hard nature problem, classical optimization not sufficient. Instead, metaheuristic heuristic widely used. addition, ever-changing big data IoE environments requires specific methods. systematic review, we present taxonomy problem. Our findings show 96% distributed architecture. Also, 51% studies on-demand resource estimation 81% multi-objective. This article also outlines open questions future research trends. literature review shows one important trends reinforcement learning, with 56% share research.

Language: Английский

Citations

14
A Survey of Security Strategies in Federated Learning: Defending Models, Data, and Privacy DOI Creative Commons
Habib Ullah Manzoor,

Attia Shabbir,

Ao Chen

et al.

Future Internet, Journal Year: 2024, Volume and Issue: 16(10), P. 374 - 374

Published: Oct. 15, 2024

Federated Learning (FL) has emerged as a transformative paradigm in machine learning, enabling decentralized model training across multiple devices while preserving data privacy. However, the nature of FL introduces significant security challenges, making it vulnerable to various attacks targeting models, data, and This survey provides comprehensive overview defense strategies against these attacks, categorizing them into defenses privacy attacks. We explore pre-aggregation, in-aggregation, post-aggregation defenses, highlighting their methodologies effectiveness. Additionally, delves advanced techniques such homomorphic encryption differential safeguard sensitive information. The integration blockchain technology for enhancing environments is also discussed, along with incentive mechanisms promote active participation among clients. Through this detailed examination, aims inform guide future research developing robust frameworks systems.

Language: Английский

Citations

10
A Scalable Framework for Sensor Data Ingestion and Real-Time Processing in Cloud Manufacturing DOI Creative Commons
Massimo Pacella, A. Papa, Gabriele Papadia

et al.

Algorithms, Journal Year: 2025, Volume and Issue: 18(1), P. 22 - 22

Published: Jan. 4, 2025

Cloud Manufacturing enables the integration of geographically distributed manufacturing resources through advanced Computing and IoT technologies. This paradigm promotes development scalable adaptable production systems. However, existing frameworks face challenges related to scalability, resource orchestration, data security, particularly in rapidly evolving decentralized settings. study presents a novel nine-layer architecture designed specifically address these issues. Central this framework is use Apache Kafka for robust, high-throughput ingestion, Spark Streaming enhance real-time processing. underpinned by microservice-based that ensures high scalability reduced latency. Experimental validation using sensor from UCI Machine Learning Repository demonstrated substantial improvements processing efficiency throughput compared with conventional frameworks. Key components, such as RabbitMQ, contribute low-latency performance, whereas durability supports application. Additionally, in-memory rapid dynamic analysis, yielding actionable insights. The experimental results highlight potential operational efficiency, utilization, offering resilient solution suited demands modern industrial applications. underscores contribution advancing providing detailed insights into its applicability contemporary ecosystems.

Language: Английский

Citations

1
Federated learning-empowered smart manufacturing and product lifecycle management: A review DOI
Jiewu Leng, Richard Li,

Junxing Xie

et al.

Advanced Engineering Informatics, Journal Year: 2025, Volume and Issue: 65, P. 103179 - 103179

Published: Feb. 10, 2025

Language: Английский

Citations

1
Beyond the Cloud: Federated Learning and Edge AI for the Next Decade DOI Open Access

Sooraj George Thomas,

Praveen Kumar Myakala

Journal of Computer and Communications, Journal Year: 2025, Volume and Issue: 13(02), P. 37 - 50

Published: Jan. 1, 2025

Language: Английский

Citations

1
Federated learning using game strategies: State-of-the-art and future trends DOI

Rajni Gupta,

J. P. Gupta

Computer Networks, Journal Year: 2023, Volume and Issue: 225, P. 109650 - 109650

Published: Feb. 23, 2023

Language: Английский

Citations

17