SafetyMed: A Novel IoMT Intrusion Detection System Using CNN-LSTM Hybridization

Electronics, Journal Year: 2023, Volume and Issue: 12(17), P. 3541 - 3541

Published: Aug. 22, 2023

The Internet of Medical Things (IoMT) has become an attractive playground to cybercriminals because its market worth and rapid growth. These devices have limited computational capabilities, which ensure minimum power absorption. Moreover, the manufacturers use simplified architecture offer a competitive price in market. As result, IoMTs cannot employ advanced security algorithms defend against cyber-attacks. IoMT easy prey for due access valuable data rapidly expanding market, as well being comparatively easier exploit.As intrusion rate is experiencing surge. This paper proposes novel Intrusion Detection System (IDS), namely SafetyMed, combining Convolutional Neural Networks (CNN) Long Short-Term Memory (LSTM) networks from sequential grid data. SafetyMed first IDS that protects malicious image network traffic. innovative ensures optimized detection by trade-off between False Positive Rate (FPR) (DR). It detects intrusions with average accuracy 97.63% precision recall, F1-score 98.47%, 97%, 97.73%, respectively. In summary, potential revolutionize many vulnerable sectors (e.g., medical) ensuring maximum protection intrusion.

Language: Английский

---

Cyber-Physical System Security Based on Human Activity Recognition through IoT Cloud Computing

Electronics, Journal Year: 2023, Volume and Issue: 12(8), P. 1892 - 1892

Published: April 17, 2023

Cyber-physical security is vital for protecting key computing infrastructure against cyber attacks. Individuals, corporations, and society can all suffer considerable digital asset losses due to attacks, including data loss, theft, financial reputation harm, company interruption, damage, ransomware espionage. A cyber-physical attack harms both physical assets. system more challenging than software-level because it requires inspection monitoring. This paper proposes an innovative effective algorithm strengthen (CPS) with minimal human intervention. It approach based on activity recognition (HAR), where GoogleNet–BiLSTM network hybridization has been used recognize suspicious activities in the perimeter. The proposed HAR-CPS classifies from real-time video surveillance average accuracy of 73.15%. incorporates machine vision at IoT edge (Mez) technology make latency tolerant. Dual-layer ensured by operating hybrid a cloud server, which ensures system. optimization scheme makes possible only USD 4.29±0.29 per month.

Language: Английский

---

A Novel IDS with a Dynamic Access Control Algorithm to Detect and Defend Intrusion at IoT Nodes

Sensors, Journal Year: 2024, Volume and Issue: 24(7), P. 2188 - 2188

Published: March 29, 2024

The Internet of Things (IoT) is the underlying technology that has enabled connecting daily apparatus to and enjoying facilities smart services. IoT marketing experiencing an impressive 16.7% growth rate a nearly USD 300.3 billion market. These eye-catching figures have made it attractive playground for cybercriminals. devices are built using resource-constrained architecture offer compact sizes competitive prices. As result, integrating sophisticated cybersecurity features beyond scope computational capabilities IoT. All these contributed surge in intrusion. This paper presents LSTM-based Intrusion Detection System (IDS) with Dynamic Access Control (DAC) algorithm not only detects but also defends against novel approach achieved 97.16% validation accuracy. Unlike most IDSs, model proposed IDS been selected optimized through mathematical analysis. Additionally, boasts ability identify wider range threats (14 be exact) compared other solutions, translating enhanced security. Furthermore, fine-tuned strike balance between accurately flagging minimizing false alarms. Its performance metrics (precision, recall, F1 score all hovering around 97%) showcase potential this innovative elevate detection rate, exceeding 98%. high accuracy instills confidence its reliability. lightning-fast response time, averaging under 1.2 s, positions among fastest intrusion systems available.

Language: Английский

---

Deep-IDS: A Real-Time Intrusion Detector for IoT Nodes Using Deep Learning

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 63584 - 63597

Published: Jan. 1, 2024

The Internet of Things (IoT) represents a swiftly expanding sector that is pivotal in driving the innovation today's smart services. However, inherent resource-constrained nature IoT nodes poses significant challenges embedding advanced algorithms for cybersecurity, leading to an escalation cyberattacks against these nodes. Contemporary research Intrusion Detection Systems (IDS) predominantly focuses on enhancing IDS performance through sophisticated algorithms, often overlooking their practical applicability. This paper introduces Deep-IDS, innovative and practically deployable Deep Learning (DL)-based IDS. It employs Long-Short-Term-Memory (LSTM) network comprising 64 LSTM units trained CIC-IDS2017 dataset. Its streamlined architecture renders Deep-IDS ideal candidate edge-server deployment, acting as guardian between Denial Service (DoS), Distributed (DDoS), Brute Force (BRF), Man-in-the-Middle (MITM), Replay (RP) Attacks. A distinctive aspect this trade-off analysis intrusion detection rate false alarm rate, facilitating real-time Deep-IDS. system demonstrates exemplary 96.8% overall classification accuracy 97.67%. Furthermore, achieves precision, recall, F1-scores 97.67%, 98.17%, 97.91%, respectively. On average, requires 1.49 seconds identify mitigate attempts, effectively blocking malicious traffic sources. remarkable efficacy, swift response time, design, novel defense strategy not only secure but also interconnected sub-networks, thereby positioning IoT-enhanced computer networks.

Language: Английский

---

A two stage blood cell detection and classification algorithm based on improved YOLOv7 and EfficientNetv2

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

Published: March 11, 2025

Language: Английский

---

Confimizer: A Novel Algorithm to Optimize Cloud Resource by Confidentiality-Cost Trade-Off Using BiLSTM Network

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 89205 - 89217

Published: Jan. 1, 2023

The world is expiring a 23% annual data growth rate and projected to have total surplus volume of 175 Zettabytes by 2025. It imposes significant challenges for small medium-sized businesses allocate funds large-size storage. initial large upfront maintenance costs made cloud storage services popular. comes with confidentiality concerns. Encrypting before storing it in the most effective solution this challenge. decrypting volumes massive amounts expensive resources. Storing plain text reduces system load expenditure but introduces This paper proposed Confimizer, novel algorithm, optimize resources reduce balancing trade-off between cost. overload 13.75%, saving 9.20% expenditure. saves 12.33% API calls 52.99%. Confimizer uses an optimized BiLSTM network that classifies according level 84.00% accuracy, 76.92% precision, 74.47% recall, 75.01 F1 score. innovative approach, architecture, outstanding performance make unique resource optimization algorithm.

Language: Английский

---

An Optimized Question Classification Framework Using Dual-Channel Capsule Generative Adversarial Network and Atomic Orbital Search Algorithm

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 75736 - 75747

Published: Jan. 1, 2023

The advancement in education has emphasized the need to evaluate quality of examination questions and cognitive levels students. Many educational institutions now acknowledge Bloom's taxonomy-based students' evaluating subject-related learning. Therefore, this paper, a novel optimized Examination Question Classification framework, referred as QC-DcCapsGANAOSA, is proposed by combining Dual-channel Capsule generative Adversarial Network (DcCapsGAN) with Atomic Orbital Search Algorithm (AOSA) for preprocessing real-time online dataset university questions, thus identify key features from raw data using Term Frequency Inverse Document (TF-IDF) finally classifying questions. used fine-tune parameters' weights DcCapsGAN, then uses these categorize Knowledge Level, Comprehension Application Analysis Synthesis Evaluation Level. Experimental results demonstrate superiority method (QC-DuCapsGAN-AOSA) when compared state-of-the-art methods such QC-LSTM-CNN QC-BiGRU-CNN an accuracy improvement 23.65% 29.04%, respectively.

Language: Английский

---

AI and National Security: The Geopolitical Implications of Autonomous Weapons and Cyber security

Published: Oct. 20, 2023

A. Overview of AI's role in national securityArtificial Intelligence (AI) has emerged as a transformative force the realm security. The use AI technologies, such machine learning, natural language processing, and computer vision, become integral to various aspects nation's security apparatus. extends areas like intelligence gathering, threat analysis, decision-making support, operational effectiveness. It potential enhance military capabilities, improve cybersecurity, revolutionize way governments safeguard their interests.B. Significance autonomous weapons cybersecurity geopolitical contextAutonomous have risen forefront discussions surrounding security, implications on stage are profound. Autonomous weapons, including drones robots, can operate without direct human control, raising ethical, legal, strategic concerns. Their deployment change dynamics armed conflict, affecting how states engage warfare altering balance power among nations.Cybersecurity, other hand, is critical component digital landscape becomes battlefield its own. AI-driven cyberattacks defenses disrupt infrastructure, steal sensitive data, manipulate public perception. interplay lead both offensive defensive strategies, with vying protect assets exploit vulnerabilities adversaries' networks.This paper will explore these two key focusing they impact international relations, doctrines, arms control agreements, overall stability global landscape. By examining significance context we better understand evolving geopolitics 21st century.

Language: Английский

---

Quantum Machine Learning: The Confluence of Quantum Computing and AI

Published: Oct. 20, 2023

Quantum Machine Learning (QML) represents the juncture of quantum computing and artificial intelligence, ushering in a new era computation data analysis. This abstract explores convergence these two groundbreaking fields its implications for future AI.In QML, bits (qubits) harness unique properties superposition entanglement, enabling simultaneous exploration vast solution spaces. algorithms, such as Support Vector Machines Neural Networks, promise exponential speedup range AI tasks.However, QML is not without challenges. hardware, including processors annealers, must contend with issues error correction scalability. Ethical security considerations also loom large development application machine learning.As technology matures, holds potential to redefine boundaries opening frontiers analysis, optimization, problem-solving. encapsulates transformative possibilities challenges presented by confluence realm Learning.

Language: Английский

---

Higher Educational Institution (HEI) Promotional Management Support System Through Sentiment Analysis for Student Intake Improvement

IEEE Access, Journal Year: 2023, Volume and Issue: 11, P. 77779 - 77792

Published: Jan. 1, 2023

Promotional activities with Emotional Intelligence (EI) are more effective than factual information. It is significant in Higher Educational Institutions (HEIs) marketing and reputation management. Choosing an HEI a crucial decision. Factual information ignites the human brain's analytical characteristics, making logical decisions while choosing HEI. that target emotional states push group to overlook logic make decisions. This paper presents novel Management Support (PMS) system utilizes this phenomenon through sentiment analysis enhance capabilities. A Bi-Directional-Long-Short-Term-Memory (BiLSTM) network has been designed implemented classify existing students' sentiments into four classes. classifies average accuracy of 92.75%. The positive students used promotional content, whereas negative guides avoid content probability raising concerns. application PMS demonstrates 4.78% improvement student intake over observational period 24 months. unique concept, implementation, remarkable result indicate proposed System revolutionary Artificial (AI) improve rate.

Language: Английский

---