Review
Computer Science, Information Systems
Ayesha S. Dina, D. Manivannan
Summary: Intrusions in computer networks have been on the rise in the past decade, leading researchers to propose signature-based and anomaly-based intrusion detection methods, with Machine Learning techniques playing a key role. This paper provides a comprehensive critical survey of ML-based intrusion detection approaches in the literature over the last ten years, highlighting some open issues for future research.
INTERNET OF THINGS
(2021)
Article
Computer Science, Information Systems
Raniyah Wazirali, Rami Ahmad
Summary: This paper investigates the use of machine learning algorithms for securing wireless sensor networks and evaluates their performance. The results show that the Gboost algorithm performs the best and has specific requirements for dataset size and category distribution. Additionally, the paper explores the impact of Gboost on the lifetime of wireless sensor networks.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)
Article
Computer Science, Theory & Methods
Souradip Roy, Juan Li, Bong-Jin Choi, Yan Bai
Summary: The increasing popularity of the Internet of Things has led to more security breaches associated with vulnerable IoT devices, emphasizing the importance of employing intrusion detection techniques. Traditional intrusion detection mechanisms may not work well for IoT environments, leading to the proposal of a novel intrusion detection model utilizing machine learning. Through optimizations such as removal of multicollinearity and dimensionality reduction, the model shows promising results with high detection rates and low false alarm rates in experiments on popular datasets.
FUTURE GENERATION COMPUTER SYSTEMS-THE INTERNATIONAL JOURNAL OF ESCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
M. Hema Kumar, V Mohanraj, Y. Suresh, J. Senthilkumar, G. Nagalalli
Summary: The method introduces a novel trust aware localized routing and class based dynamic encryption scheme to enhance data security and improve overall network performance.
JOURNAL OF AMBIENT INTELLIGENCE AND HUMANIZED COMPUTING
(2021)
Article
Chemistry, Analytical
Mohammed M. Alani, Ali Miri
Summary: With the rapid growth of IoT devices' adoption, security has become increasingly important. In order to counter security threats, we propose an explainable and efficient method to select the most effective features for building highly accurate intrusion detection systems in IoT.
Article
Computer Science, Hardware & Architecture
Joseph R. Rose, Matthew Swann, Konstantinos P. Grammatikakis, Ioannis Koufos, Gueltoum Bendiab, Stavros Shiaeles, Nicholas Kolokotronis
Summary: The widespread use of IoT devices brings many benefits to society, but also poses cybersecurity risks. This paper explores the potential of using network profiling, machine learning, and game theory to secure IoT against cyber attacks, proposing an anomaly-based intrusion detection solution.
JOURNAL OF SYSTEMS ARCHITECTURE
(2022)
Article
Computer Science, Information Systems
Muawia A. Elsadig
Summary: The characteristics and performance of wireless sensor networks (WSNs) are the main reasons for their rapid expansion in various fields. However, these networks are extremely vulnerable to security attacks, especially denial-of-service (DoS) attacks. This study focuses on understanding the limitations, weaknesses, and security threats of WSNs, with a specific emphasis on DoS attacks. It explores recent techniques for detecting DoS attacks and proposes a lightweight machine learning approach based on the decision tree algorithm to address this issue. The proposed approach achieves high accuracy and significantly outperforms other classifiers in terms of processing time.
Article
Chemistry, Multidisciplinary
Gianmarco Baldini, Jose Luis Hernandez Ramos, Irene Amerini
Summary: This study proposes a new anomaly detection algorithm for IDS, utilizing machine learning to detect intrusions. The method transforms network flow statistics into grayscale images and uses GLCM and 2D Dispersion Entropy for analysis.
APPLIED SCIENCES-BASEL
(2021)
Article
Chemistry, Multidisciplinary
Sara Amaouche, Azidine Guezzaz, Said Benkirane, Mourade Azrour, Sohaib Bin Altaf Khattak, Haleem Farman, Moustafa M. Nasralla
Summary: Vehicular ad hoc networks (VANETs) are used for vehicle to vehicle (V2V) and vehicle to infrastructure (V2I) communications to improve road traffic and safety. However, VANETs face network attacks and communication challenges in dynamic environments. Therefore, securing communication in VANETs is crucial.
APPLIED SCIENCES-BASEL
(2023)
Article
Computer Science, Information Systems
Souradip Roy, Juan Li, Yan Bai
Summary: In this paper, the authors investigate intrusion detection techniques for IoT networks and propose a machine learning-based two-layer hierarchical intrusion detection mechanism. The proposed approach outperforms existing methods in terms of accuracy and performance, and offers advantages in improving service time, reducing delay, and optimizing energy utilization.
INTERNET OF THINGS
(2022)
Article
Computer Science, Information Systems
Jaskaran Singh, Mohammad Wazid, Ashok Kumar Das, Vinay Chamola, Mohsen Guizani
Summary: Cyber physical systems integrate sensing, computation, control, and networking processes into physical objects and infrastructure. The tight coupling of cyber systems with physical systems introduces challenges in stability, security, efficiency, and reliability. Machine learning security aims to protect machine learning models against various cyber attacks. In this article, various machine learning security attacks in cyber physical systems are discussed, along with defense mechanisms and a comparative study of ML models' performance under the influence of these attacks.
COMPUTER COMMUNICATIONS
(2022)
Article
Engineering, Electrical & Electronic
Hideya Ochiai, Md Delwar Hossain, Pawissakan Chirupphapa, Youki Kadobayashi, Hiroshi Esaki
Summary: In this article, a novel unobtrusive communication signal monitoring method was proposed for attack detection on Modbus/RS-485 field buses using machine learning. Five types of field-bus attacks were defined and datasets with ground truth labels were developed. The proposed method achieved high detection rates for attack detection according to the performance evaluation results.
IEEE COMMUNICATIONS MAGAZINE
(2023)
Article
Computer Science, Hardware & Architecture
Gianmarco Baldini, Irene Amerini
Summary: This paper proposes an online algorithm based on a sliding window with the novel application of the Morphological Fractal Dimension (MFD) to improve the detection accuracy of Distributed Denial of Service (DDOS) attacks. The experimental results show that this method outperforms other similar approaches in terms of detection accuracy.
Article
Computer Science, Information Systems
Imran Ashraf, Manideep Narra, Muhammad Umer, Rizwan Majeed, Saima Sadiq, Fawad Javaid, Nouman Rasool
Summary: Intrusion detection systems are crucial for providing high-level network security, especially with the increasing sophistication of network attacks. This study proposes an approach that combines machine learning models to enhance intrusion detection performance in the modern network environment.
Article
Chemistry, Multidisciplinary
Murat Dener, Abdullah Orman
Summary: Wireless Sensor Networks (WSNs), as an important part of IoT, consist of sensor nodes with limited processing, memory capacities, and energy. The security of WSNs is often questioned due to the dangers they face in untrusted regions. This study aims to develop a new blockchain-based authentication protocol for WSNs to address the deficiencies in existing authentication protocols and utilize the security characteristics of blockchain.
APPLIED SCIENCES-BASEL
(2023)
Editorial Material
Multidisciplinary Sciences
Selvi Munuswamy, M. S. Saranya, S. Ganapathy, S. Muthurajkumar, A. Kannan
Summary: The study introduces a sentiment-based rating prediction method that accurately predicts items liked by users. By calculating individual user sentiments on items and computing item reputations based on these three sentiments, accurate recommendations can be provided.
NATIONAL ACADEMY SCIENCE LETTERS-INDIA
(2021)
Article
Telecommunications
Rajasoundaran Soundararajan, S. Rakesh Kumar, N. Gayathri, Fadi Al-Turjman
Summary: The proposed system aims to classify highly preferable products in online marketplaces efficiently, by using decision-making strategies. It evaluates popular products and product groups, analyses online market growth, predicts market prices, and adds new packages at optimal prices to the database. The system focuses on user-based ratings and provides a controlled performance in selecting preferable products.
WIRELESS PERSONAL COMMUNICATIONS
(2021)
Review
Telecommunications
S. Rajasoundaran, A. V. Prabu, G. Sateesh Kumar, Prince Priya Malla, Sidheswar Routray
Summary: This research focuses on analyzing problems and solutions related to secure routing and watchdog production in Wireless Sensor Networks (WSN). The study helps in understanding IDS techniques, WSN characteristics, secure routing, key management techniques, and watchdog construction strategies in detail. The findings extend to efficient cryptography techniques, attack detection algorithms, and protocols with real-time watchdogs.
WIRELESS PERSONAL COMMUNICATIONS
(2021)
Article
Computer Science, Information Systems
S. V. N. Santhosh Kumar, Yogesh Palanichamy, M. Selvi, Sannasi Ganapathy, Arputharaj Kannan, Sankar Pariserum Perumal
Summary: A novel protocol named Cluster based Secured Data dissemination Protocol (CSDP) is proposed to enhance the energy efficiency and security in Wireless Sensor Networks. By addressing security vulnerabilities and reducing energy consumption, the proposed protocol improves the reliability of communication systems and enhances network security.
Article
Telecommunications
Jacob John, Mariam Sunil Varkey, Riya Sanjay Podder, Nilavrah Sensarma, M. Selvi, S. V. N. Santhosh Kumar, Arputharaj Kannan
Summary: IoT technology in smart cities can improve city infrastructure and public services, effectively addressing waste management issues.
WIRELESS PERSONAL COMMUNICATIONS
(2022)
Article
Computer Science, Information Systems
S. Rajasoundaran, A. Prabu, Sidheswar Routray, S. V. N. Santhosh Kumar, Prince Priya Malla, Suman Maloji, Amrit Mukherjee, Uttam Ghosh
Summary: Virtual Private Cloud (VPC) is an emerging cloud environment used for secure data communication. Evaluation of cloud jobs and runtime cloud events is necessary for flawless VPC service. Secure job service schemes ensure elimination of attacks, unauthorized jobs, improper accesses and intrusions in VPC.
COMPUTERS & SECURITY
(2021)
Article
Computer Science, Software Engineering
A. Gayathri, A. V. Prabu, S. Rajasoundaran, Sidheswar Routray, P. Narayanasamy, Naween Kumar, Yinan Qi
Summary: This study proposes a cooperative and feedback-based trustable energy-efficient routing protocol (CFTEERP) to address security issues in IoT communication. The protocol calculates local and global trust values of nodes, utilizes a multipath routing strategy, and eliminates malicious nodes using the K-means clustering algorithm to improve network lifetime and data transmission efficiency.
CONCURRENCY AND COMPUTATION-PRACTICE & EXPERIENCE
(2022)
Article
Computer Science, Artificial Intelligence
A. Prabu, G. Sateesh Kumar, Soundararajan Rajasoundaran, Prince Priya Malla, Sidheswar Routray, Amrit Mukherjee
Summary: The proposed IoT based crop field protection system aims to monitor and protect crop fields using deep learning techniques, providing automatic alerts to prevent animal intrusions and crop diseases, and ultimately increase crop production. The system utilizes sensor nodes, cameras, and agriculture drones to collect field data regularly and trains RCNN and RGAN units for faster and more accurate decision-making. Experiment results show that the proposed ICFPS achieves 8%-10% higher classification accuracy compared to existing systems.
Article
Computer Science, Information Systems
S. Rajasoundaran, A. Prabu, Sidheswar Routray, Prince Priya Malla, G. Sateesh Kumar, Amrit Mukherjee, Yinan Qi
Summary: This paper proposes a dynamic multi-watchdog system based on deep learning, which uses DCNN and DPFES to construct a secure and cooperative multi-watchdog system, protecting each sensor node and expanding the secure medium of 5G-based IoT-WSN networks.
COMPUTER COMMUNICATIONS
(2022)
Article
Energy & Fuels
Vishnu Kumar Kaliappan, Seungjin Yu, Rajasoundaran Soundararajan, Sangwoo Jeon, Dugki Min, Enumi Choi
Summary: This article presents a distributed system framework called SeDIS-HEB, which utilizes homomorphic encryption and blockchain for secure Docker image sharing. The framework prioritizes secure upload, sharing, and download functions, and is evaluated using IPFS.
Article
Computer Science, Information Systems
S. Rajasoundaran, Santhosh S. V. N. Kumar, M. Selvi, Sannasi Ganapathy, A. Kannan
Summary: This paper proposes three image compression algorithms based on ensemble machine learning and deep learning techniques. The algorithms accurately identify the dependencies and unimportant regions of image blocks, improving compression ratio and reducing noise in comparison to existing methods.
MULTIMEDIA TOOLS AND APPLICATIONS
(2022)
Article
Chemistry, Analytical
Rajasoundaran Soundararajan, Maheswar Rajagopal, Akila Muthuramalingam, Eklas Hossain, Jaime Lloret
Summary: This study proposes a new wireless honeypot detection model that combats various attacks by introducing a distributed honeypot mechanism and secure hash-based random frame-interleaving principles against channel attackers. Simulation and experimental results demonstrate that the proposed model outperforms existing techniques.
Article
Energy & Fuels
Dharmesh Dhabliya, Rajasoundaran Soundararajan, Parthiban Selvarasu, Maruthi Shankar Balasubramaniam, Anand Singh Rajawat, S. B. Goyal, Maria Simona Raboaca, Traian Candin Mihaltan, Chaman Verma, George Suciu
Summary: Wireless sensor networks (WSNs) are widely used for various environmental sensing applications. To improve the performance of WSNs, energy optimization and load balancing are needed. This paper conducts a literature review and experimental comparisons on energy-efficient MAC protocols, channel scheduling policies, and energy-efficient routing protocols. The results show that cross-layer or multi-layer energy optimization policies perform better than homogeneous energy optimization models.
Article
Computer Science, Information Systems
Peiying Zhang, Peng Gan, Lunjie Chang, Wu Wen, M. Selvi, Godfrey Kibalya
Summary: Mobile edge computing is widely used in IoT devices. This study proposes a task offloading strategy based on differential privacy and reinforcement learning, which optimizes the overhead and protects user privacy, improving the performance of mobile edge computing in terms of security and resource consumption.