Securing the Future of IoMT

Advances in healthcare information systems and administration book series, Journal Year: 2025, Volume and Issue: unknown, P. 191 - 216

Published: Jan. 17, 2025

Integrating Internet of Things (IoT) technologies into healthcare has brought about a new era characterized by enhanced connectivity and efficiency. However, this transformation also introduces significant challenges in safeguarding medical information. This analysis focuses on the interconnected network devices systems. It covers various types data, including Personal Health Information (PHI) telemetry susceptible to threats such as unauthorized access, data breaches, exploitation IoT vulnerabilities. The research emphasizes need for proactive adaptable security measures. Technological solutions secure storage systems communication channels are analyzed provide holistic understanding tools available mitigating risks. Finally, paper explores future trends using Dynamic Attribute-Based Encryption Scheme (DABES), which enables fine-grained access control data.

Language: Английский

---

Defending Against Multifaceted Network Attacks: A Multi-Label Meta-Learning and Lorenz Chaos MTD based Security Paradigm

Journal of Network and Systems Management, Journal Year: 2025, Volume and Issue: 33(2)

Published: March 24, 2025

Language: Английский

---

A deep Reinforcement learning-based robust Intrusion Detection System for securing IoMT Healthcare Networks

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: April 8, 2025

The Internet of Medical Things (IoMT) is transforming healthcare by enabling continuous remote patient monitoring, diagnostics, and personalized therapies. However, the widespread deployment these devices introduces significant security vulnerabilities due to limited resources inadequate network protocols. Intrusions within IoMT networks can compromise privacy, disrupt critical medical services, jeopardize safety. To address challenges, we propose HCLR-IDS, an advanced Intrusion Detection System (IDS) specifically designed for networks. system integrates Convolutional Neural Networks (CNN), Long Short-Term Memory (LSTM) networks, Reinforcement Learning (RL) techniques, namely Deep Q-Network (DQN) Proximal Policy Optimization (PPO), enhance detection evolving threats. methodology begins with Enhanced Mutual Information Feature Selection (MIFS) preprocess CICIoMT2024 dataset, selecting most relevant features while reducing noise computational complexity. These selected are then passed through a hybrid CNN-LSTM architecture. CNN captures spatial patterns in traffic, LSTM identifies temporal patterns. This dual feature extraction approach enables effectively detect both static dynamic characteristics data. After extraction, model incorporates DQN PPO decision-making. optimizes actions based on Q-values, enhancing rewards, ensures stability environments clipping mechanism. combination adaptive Q-learning stable policy optimization significantly improves robustness, ensuring effective real-time intrusion detection. demonstrates exceptional performance binary classification accuracy 0.9958, outperforming traditional IDS models. Additionally, it performs multi-class across 18 classes, achieving 0.7773. results highlight that HCLR-IDS offers reliable efficient solution securing systems.

Language: Английский

---

Network Security and Privacy Protection in Cyberattacks With Asynchronous Reinforcement Federated Learning With Task Offloading: Decentralized Real‐Time Iteration Approach

Journal of Sensors, Journal Year: 2025, Volume and Issue: 2025(1)

Published: Jan. 1, 2025

Medical healthcare has experienced a revolution through the Internet of Things (IoMT) system, which needs crucial improvements for security measures while working towards better privacy and efficiency capabilities. This paper develops asynchronous reinforcement federated learning (FL) with task offloading (ARFL‐TO) as combination FL (RL) dynamic TO systems to boost scalability alongside adaptability in heterogeneous environments, including autonomous systems, smart grids, industrial (IIoT) settings. ARFL‐TO requires validation different datasets, encompass range disease groups together multiple medical instruments. The analysis indicates that surpasses FL‐TO reinforcement‐based fusion (FRF) productivity by 42.22% reduces power requirements 79.22% shortening processing time 7.13% during real‐world operation, where networks become unstable data transmission is affected. framework achieves protection secure pooling, it makes models understandable clinical support addition delivering enhanced energy low‐power devices. Future investigation directs toward integrating proposed system into real environments developing performance severe operational scenarios, introducing adaptable hyperparameter techniques suitable requiring adjustments. establishes itself an efficient time‐sensitive decision‐making across decentralized cross‐sectoral maintaining concerns.

Language: Английский

---

Blockchain-Driven Incentive Mechanism and Multi-Level Federated Learning Method for Behavior Detection in the Internet of Vehicles

Symmetry, Journal Year: 2025, Volume and Issue: 17(5), P. 669 - 669

Published: April 28, 2025

With the rapid advancement of intelligent transportation systems (ITSs), behavior detection within Internet Vehicles (IoVs) has become increasingly critical for maintaining system security and operational stability. However, existing approaches face significant challenges related to data privacy, node trustworthiness, transparency. To address these limitations, this study proposes a blockchain-driven federated learning framework anomaly in IoV environments. A reputation evaluation mechanism is introduced quantitatively assess credibility contribution connected autonomous vehicles (CAVs), thereby enabling more effective management incentive regulation. In addition, multi-level model aggregation strategy based on dynamic vehicle selection developed integrate local models efficiently, with optimal global securely recorded blockchain ensure immutability traceability. Furthermore, reputation-based prepaid reward designed improve resource utilization, enhance participant loyalty, strengthen overall resilience. Experimental results confirm that proposed achieves high accuracy selects participating nodes up 99% reliability, validating its effectiveness practicality deployment real-world scenarios.

Language: Английский

---

Cyber Security in Healthcare Systems: A Review of Tools and Attack Mitigation Techniques

Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 87 - 105

Published: Jan. 1, 2025

Language: Английский

---

Velocity Paused Particle Swarm Optimization-based Intelligent Long Short-Term Memory Framework for Intrusion Detection System in Internet of Medical Things

Arabian Journal for Science and Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 26, 2025

Language: Английский

---

LSTM-JSO framework for privacy preserving adaptive intrusion detection in federated IoT networks

Scientific Reports, Journal Year: 2025, Volume and Issue: 15(1)

Published: April 2, 2025

Language: Английский

---

Cybersecurity Issues on E-Healthcare Cloud Data Warehouse System

Advances in computational intelligence and robotics book series, Journal Year: 2025, Volume and Issue: unknown, P. 125 - 154

Published: March 7, 2025

In order to detect denial-of-service (DoS) and distributed denial of service (DDoS) intrusions on the organization's e-healthcare data warehouse infrastructure, authors this study proposed a computing framework that combines federated learning system based blockchain technology. A Message Queuing Telemetry Transport (MQTT) broker gathers from an IoT node sends it platform for analysis. As creation several new technologies applications, has created opportunities in age cloud communication. Due increasing use technologies, computer networks have had serious security concerns, there are vulnerabilities as well. DoS DDoS attacks servers may compromise general stability, efficacy services, real-time information federation. This provided efficient MQTT approach secure cyberattacks presented state-of-the-art defenses against DoS/DDoS digital healthcare ecosystem.

Language: Английский

---

Internet of Medical Things Systems Review: Insights into Non-Functional Factors

Sensors, Journal Year: 2025, Volume and Issue: 25(9), P. 2795 - 2795

Published: April 29, 2025

Internet of Medical Things (IoMT) is a rapidly evolving field with the potential to bring significant changes healthcare. While several surveys have examined structure and operation these systems, critical aspects such as interoperability, sustainability, security, runtime self-adaptation, configurability are sometimes overlooked. Interoperability essential for integrating data from various devices platforms provide comprehensive view patient’s health. Sustainability addresses environmental impact IoMT technologies, crucial in context green computing. Security ensures protection sensitive patient breaches manipulation. Runtime self-adaptation allows systems adjust changing conditions environments. Configurability enables frameworks monitor diverse manage different treatment paths. This article reviews current techniques addressing highlights areas requiring further research.

Language: Английский

---