A deep learning-based novel hybrid CNN-LSTM architecture for efficient detection of threats in the IoT ecosystem

Ain Shams Engineering Journal, Год журнала: 2024, Номер 15(7), С. 102777 - 102777

Опубликована: Апрель 4, 2024

The Internet of Things (IoT) landscape is witnessing rapid growth, driven by continuous innovation and a simultaneous increase in cybersecurity threats. As these threats become more sophisticated, the imperative to fortify IoT devices against emerging vulnerabilities becomes increasingly pronounced. This research motivated need for comprehensive threat detection solutions that can effectively address evolving landscape. Existing approaches often fall short adapting dynamic nature environments increasing complexity attacks. core problem addressed this development novel Hybrid Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) architecture tailored precise efficient detection. aims overcome limitations existing methods enhance security ecosystems. Our study encompasses detailed analysis proposed CNN-LSTM model, leveraging data from diverse datasets, including IoT-23, N-BaIoT, CICIDS2017. model tested validated on than 14 attack types. We have designed exhibit robust capabilities capturing analyzing data. outcomes our showcase remarkable accuracy, with models achieving 95% accuracy IoT-23 dataset an outstanding 99% both N-BaIoT CICIDS2017 datasets. These findings underscore model's adaptability various environments. contributes significantly enhances introduce Principal Component Analysis (PCA) optimize processing incorporate advanced optimization techniques like quantization pruning improve deployment efficiency resource-constrained lays foundation future advancements bolstering security.

Язык: Английский

---

Healthcare As a Service (HAAS): CNN-based cloud computing model for ubiquitous access to lung cancer diagnosis

Heliyon, Год журнала: 2023, Номер 9(11), С. e21520 - e21520

Опубликована: Окт. 27, 2023

The field of automated lung cancer diagnosis using Computed Tomography (CT) scans has been significantly advanced by the precise predictions offered Convolutional Neural Network (CNN)-based classifiers. Critical areas study include improving image quality, optimizing learning algorithms, and enhancing diagnostic accuracy. To facilitate a seamless transition from research laboratories to real-world applications, it is crucial improve technology's usability-a factor often neglected in current state-of-the-art research. Yet, this frequently overlooks need for expediting process. This paper introduces Healthcare-As-A-Service (HAAS), an innovative concept inspired Software-As-A-Service (SAAS) within cloud computing paradigm. As comprehensive service system, HAAS potential reduce mortality rates providing early opportunities everyone. We present HAASNet, cloud-compatible CNN that boasts accuracy rate 96.07%. By integrating HAASNet with physio-symptomatic data Internet Medical Things (IoMT), proposed model generates accurate reliable reports. Leveraging IoMT technology, globally accessible via Internet, transcending geographic boundaries. groundbreaking achieves average precision, recall, F1-scores 96.47%, 95.39%, 94.81%, respectively.

Язык: Английский

---

An RFE/Ridge-ML/DL based anomaly intrusion detection approach for securing IoMT system

Results in Engineering, Год журнала: 2024, Номер 23, С. 102659 - 102659

Опубликована: Авг. 2, 2024

Smart healthcare is one of the promising areas Internet Things (IoT), particularly in case Covid-19 pandemic. Real-time patient monitoring and remote diagnostics facilitate better medical services to preserve human lives using Medical (IoMT) technology. Regardless numerous benefits, IoMT devices are susceptible sophisticated cyber-attacks at a breakneck pace, which lead tampering with data threaten patients' lives. In similar context, 2022 ransomware cyber-attack on Versailles André-Mignot Hospital compromised system disclosed tremendous amounts information. Towards this direction, most researchers have solely developed either machine learning or Deep algorithms identify network traffic anomalies. Motivated by above challenges, an effort has been made paper design Recursive Feature Elimination (RFE) integrated paradigms Ridge regression merged into deep models for implementing accurate anomaly intrusion detection based real-time dataset WUSTL-EHMS. Among used, proposed approach confirms that RFE-based Decision Tree (DT) outperforms state-of-the-art techniques training accuracy 99 % testing 97.85 while maintaining reduction FAR 0.03. nutshell, it proven suggested framework can be deployed build detection, reinforcing against widespread safeguarding integrity advanced systems.

Язык: Английский

---

A Comparative Study of Anomaly Detection Techniques for IoT Security Using Adaptive Machine Learning for IoT Threats

IEEE Access, Год журнала: 2024, Номер 12, С. 14719 - 14730

Опубликована: Янв. 1, 2024

Anomaly detection is a critical aspect of various applications, including security, healthcare, and network monitoring. In this study, we introduce FusionNet, an innovative ensemble model that combines the strengths multiple machine learning algorithms, namely Random Forest, K-Nearest Neighbors, Support Vector Machine, Multi-Layer Perceptron, for enhanced anomaly detection. FusionNet's architecture leverages diversity these algorithms to achieve high accuracy precision. We evaluate performance on two distinct datasets, Dataset 1 2, compare it with traditional models, SVM, KNN, RF. The results demonstrate FusionNet consistently outperforms models across both datasets in terms accuracy, precision, recall, F1 score. On 1, achieves 98.5% attains 99.5%. remarkable ability detect anomalies exceptional underscores its potential real-world applications. This study highlights significance as robust provides insights into superior over models. emphasize promising prospects other domains where accurate crucial.

Язык: Английский

---

Hybrid deep learning-based cyberthreat detection and IoMT data authentication model in smart healthcare

Future Generation Computer Systems, Год журнала: 2025, Номер unknown, С. 107711 - 107711

Опубликована: Янв. 1, 2025

Язык: Английский

---

Machine Learning for Healthcare-IoT Security: A Review and Risk Mitigation

IEEE Access, Год журнала: 2023, Номер 11, С. 145869 - 145896

Опубликована: Янв. 1, 2023

The Healthcare Internet-of-Things (H-IoT), commonly known as Digital Healthcare, is a data-driven infrastructure that highly relies on smart sensing devices (i.e., blood pressure monitors, temperature sensors, etc.) for faster response time, treatments, and diagnosis. However, with the evolving cyber threat landscape, IoT have become more vulnerable to broader risk surface (e.g., risks associated generative AI, 5G-IoT, etc.), which, if exploited, may lead data breaches, unauthorized access, lack of command control potential harm. This paper reviews fundamentals healthcare IoT, its privacy, security challenges machine learning H-IoT devices. further emphasizes importance monitoring layers such perception, network, cloud, application. Detecting responding anomalies involves various cyber-attacks protocols Wi-Fi 6, Narrowband Internet Things (NB-IoT), Bluetooth, ZigBee, LoRa, 5G New Radio (5G NR). A robust authentication mechanism based deep techniques required protect mitigate from increasing cybersecurity vulnerabilities. Hence, in this review paper, privacy mitigation strategies building resilience are explored reported.

Язык: Английский

---

SkipGateNet: A Lightweight CNN-LSTM Hybrid Model With Learnable Skip Connections for Efficient Botnet Attack Detection in IoT

IEEE Access, Год журнала: 2024, Номер 12, С. 35521 - 35538

Опубликована: Янв. 1, 2024

The rise of Internet Things (IoT) has led to increased security risks, particularly from botnet attacks that exploit IoT device vulnerabilities. This situation necessitates effective Intrusion Detection Systems (IDS), are accurate, lightweight, and fast (having less inference time), designed detect in resource constrained devices. paper proposes SkipGateNet, a novel deep learning model for detecting Mirai Bashlite fog computing environments. SkipGateNet is combining 1D-Convolutional Neural Networks (CNN) Long Short-Term Memory (LSTM) layers. novelty this lies the integration 'Learnable Skip Connections'. These connections feature gating mechanisms enhance detection by focusing on relevant features ignoring irrelevant ones. They add adaptability architecture, performing selection propagating only essential deeper Tested N-BaIoT dataset, efficiently detects ten types attacks, with remarkable test accuracy 99.91%. It also compact (2596.87 KB) demonstrates quick time 8.0 milliseconds, suitable real-time implementation resource-limited settings. While evaluating its performance, parameters like precision, recall, accuracy, F1 score were considered, along statistical reliability measures Cohen's Kappa Coefficient Matthews Correlation Coefficient. highlight effectiveness challenges. compares existing models four other architectures, including two sequential CNN simple CNN+LSTM standard skip connections. surpasses all time, demonstrating superiority addressing issues.

Язык: Английский

---

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

Sensors, Год журнала: 2024, Номер 24(7), С. 2188 - 2188

Опубликована: Март 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.

Язык: Английский

---

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

IEEE Access, Год журнала: 2024, Номер 12, С. 63584 - 63597

Опубликована: Янв. 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.

Язык: Английский

---

Detecting lateral movement: A systematic survey

Heliyon, Год журнала: 2024, Номер 10(4), С. e26317 - e26317

Опубликована: Фев. 1, 2024

Within both the cyber kill chain and MITRE ATT&CK frameworks, Lateral Movement (LM) is defined as any activity that allows adversaries to progressively move deeper into a system in seek of high-value assets. Although this timely subject has been studied cybersecurity literature significant degree, so far, no work provides comprehensive survey regarding identification LM from mainly an Intrusion Detection System (IDS) viewpoint. To cover noticeable gap, systematic, holistic overview topic, not neglecting new communication paradigms, such Internet Things (IoT). The part, spanning time window eight years 53 articles, split three focus areas, namely, Endpoint Response (EDR) schemes, machine learning oriented solutions, graph-based strategies. On top that, we bring light interrelations, mapping progress field over time, offer key observations may propel research forward.

Язык: Английский

---