Browsing by Author "Haribabu, K."

Now showing 1 - 13 of 13

A data-plane approach for detecting malware in iot networks
(IEEE, 2023-02) Haribabu, K.
Data plane where all the packet processing and forwarding is done based on control plane logic can be used to monitor the network traffic along with forwarding of the packets. Security threats have become common in IoT networks. Due to the pandemic, as things have moved to virtual platforms, security at every level, including network devices, has become a major concern. Attackers try to gather as much data as possible through various means. In networking, dependence on the control plane to take forwarding decisions is inefficient when quick response is required, in cases of attack mitigation, anomaly detection, intrusion detection etc. Some of the forwarding logic in control plane can be transformed into rules at the data plane. In this work, this is achieved through programmable switches and domain specific language such as P4. A machine learning algorithm is used to train a classifier on publicly available malware dataset. These rules are used for classifying data packets. This work derives rules from a public malware traffic dataset and uses Mininet (network emulator) to emulate an IoT network, and 88% accuracy is achieved in detecting malware at the data plane.
DDoS attack detection in data plane
(Springer, 2025-04) Haribabu, K.
Distributed Denial of Service (DDoS) attacks pose significant challenges to the availability of online services, with attackers seeking to overwhelm a target’s resources by generating an overwhelming volume of traffic from multiple sources. Traditional detection methods, such as signature-based or traffic pattern analysis, often lack the adaptability required to combat evolving attack strategies effectively. This paper explores the utilization of Software-Defined Networking (SDN) and data plane programmability as a reactive and adaptive mechanism for DDoS attack detection and mitigation. By leveraging the packet-level processing capabilities of P4 (Programming Protocol-Independent Packet Processors), we propose a novel implementation that employs entropy-based detection combined with gossip algorithms for decentralized information sharing. Our approach demonstrates improved responsiveness and scalability in detecting DDoS traffic and provides a comparative analysis between epidemic-based and probability-based gossip protocols. The results highlight the strengths, limitations, and real-world feasibility of our approach.
Dyswitch: dynamic switching to enable secure and energy efficient data communication in resource constrained iot environmentattack detection in data plane
(Springer, 2025-04) Haribabu, K.
Numerous applications spanning smart health, smart cities, smart parking, smart agriculture, smart homes, and smart transportation rely extensively on internet of things (IoT) systems. These systems depend on the periodic sensing of the physical environment, employing wireless sensor networks (WSNs) to collect vast amounts of data. Given the importance of safeguarding this data against diverse attacks, traditional security mechanisms may prove impractical for resource constrained WSN devices. Lightweight cryptographic algorithms emerge as a fitting solution for such environments. This paper introduces a system proposed to dynamically transition between available lightweight cryptographic algorithms, guided by factors such as the desired security level, network status (e.g. bit error rate), and user requests. Through this dynamic adaptive approach, the proposed system ensures swift adaptability to evolving security requirements and network conditions. Moreover, this methodology highlights a nuanced integration of cryptographic algorithms, catering to the evolving needs of modern IoT environments.
Early detection of DDOS attacks in networks leveraging data plane programming
(IEEE, 2023-09) Haribabu, K.
Distributed Denial of Service (DDoS) attacks are one of the most commonly used techniques to disrupt network services today. These attacks have grown in size and frequency over the past decade and commonly target DNS infrastructure and Software as a Service (SaaS) solutions hosted on the cloud. Traditional methods for DDoS attack mitigation mostly utilize external network infrastructure to monitor traffic and detect suspicious activity. These methods however are of ten subject to issues of high latency and large memory footprint. With the rise in popularity of Software Defined Networking (SDN) and data plane programmability, these issues can be tackled as network traffic can be examined at line-rate within the forwarding devices itself. This report aims to explore the P4 data plane programming language and utilize its primitives to design an in-line traffic inspection mechanism to detect an ongoing DDoS attack. The current scheme of this implementation would be to perform an Entropy calculation of the traffic at the data plane, followed by implementing a gossip protocol to disseminate entropy information to other switches. Finally, a decision making algorithm will be used to detect the DDoS attack.
Energy efficient data communication for WSN based resource constrained IoT devices
(Elsevier, 2024-10) Haribabu, K.
In the Internet of Things (IoTs) and wireless sensor networks (WSNs), improving security and energy efficiency are key concerns. Clustering, which involves managing cluster heads, plays a pivotal role in extending network lifetime. The selection of a cluster head, responsible for data transfer between nodes, is a key aspect of network management. This paper proposes two variants of a novel algorithm designed for energy efficient communication in a resource constrained IoT environments. One variant considers remaining energy, distance, and node degree for cluster head selection, while the other focuses on remaining energy and distance only. Including node degree ensures cluster heads do not waste energy by remaining idle or performing unnecessary tasks such as the cluster head selection process in every round. The authors tested these variants against several well known algorithms using MATLAB simulation environment, evaluating factors such as operating nodes, number of clusters, transmission energy, and remaining energy. The proposed algorithm extends network lifetime by maintaining more operating nodes for longer, not changing clusters or cluster heads frequently, minimizing energy consumption for transmission, and conserving more remaining energy. Consequently, the proposed algorithm outperforms existing approaches by addressing issues like zero cluster head selection, compulsory cluster head selection in every round, avoiding cluster heads that connect to no nodes, and preventing network destabilization due to unnecessary re-elections.
An energy efficient data transmission approach in smart IOT systems
(IEEE, 2024-07) Haribabu, K.
Improving energy efficiency and maximizing network longevity are two pressing issues in the Internet of Things (IoT) and wireless sensor networks (WSN). Clustering aids in enhancing energy efficiency and extending network life. A cluster head is selected in each cluster to collect and aggregate data from its cluster members. While electing appropriate nodes as cluster heads is important, associating nodes with the elected cluster heads is another component that can aid improve the network’s longevity. In this study, the authors proposed a new algorithm belonging to the family of local search problems for performing connection migration of nodes between different cluster heads. Furthermore, the simulation environment and the toolkit developed to evaluate several Cluster Head algorithms in this simulation environment have both been presented in detail.
Evaluation of file carving tools for forensic investigation in docker containers
(IEEE, 2023-01) Haribabu, K.
Container Technology has attracted a lot of attention and is increasingly utilized to deploy the industrial applications. Containers are executable units of software which encapsulate the code along with the libraries and other dependencies in order to facilitate the code to run anywhere. They take advantage of operating system virtualization and can run anything from a small microservice or software process to a larger application. Containers are very lightweight as compared to Virtual Machines. They offer high portability with very less overhead. This emerging field of container technology has attracted a lot of attention from the community of researchers. In this paper, we have performed digital forensics on the Docker containers using file carving techniques in order to test whether the lost data from the deleted containers can be retrieved or not. For this purpose, we have used three popular file carving tools and compared their performance. The results of the experiments show that the file carving is an effective way to recover the lost data from the deleted containers.
Mmulcriapp: ML and MCDA based approach for energy efficient communication for wsn based resource constrained iot devices
(IEEE, 2025-05) Haribabu, K.
Wireless Sensor Networks (WSNs) play a crucial role in various domains like environmental monitoring, agriculture, home automation, and healthcare. However, they face challenges such as limited resources, dynamic environments, data routing issues, scalability, unreliable wireless communication, mobility, security concerns, limited bandwidth, and fault tolerance. Machine Learning (ML) techniques have been utilized to address these challenges. Additionally, Multi Criteria Decision Analysis (MCDA), a tool for making decisions involving multiple criteria, is helpful in scenarios like cluster head selection in WSNs. This paper proposes a hybrid approach that combines ML for initial rounds, followed by MCDA based mechanisms in later rounds. The approach is evaluated using metrics like energy consumption, node degree, remaining energy, sink node location, and distance metrics and shows better performance compared to the ML technique alone.
A novel approach for energy-efficient communication in a constrained IoT environment
(IEEE, 2024-07) Haribabu, K.
In the realm of the Internet of Things (IoTs) and wireless sensor networks (WSNs), two key concerns are improving security and energy efficiency. One approach to enhancing network longevity is through the implementation of clustering, which involves managing cluster heads. In this study, the authors proposed two variants of a novel algorithm for energy efficient communication in a constrained IoT environment. One variant considers the node degree while the other doesn’t consider it to improve the round speed by eliminating mandatory re-election processes. Both variants also eliminate the selection of zero cluster heads problem, specifically at the beginning or towards the end of the network. Additionally, the authors tested the performance of proposed variants against several well known algorithms based on various factors such as operating nodes, number of clusters, transmission energy, remaining energy using MATLAB simulation environment. These comparisons will give us a crucial insight into the working of the proposed algorithm and question its applicability in the real world. The results of this comparison are promising, as the proposed variant with node degree outperforms other algorithms.
Rational identification of suitable classification models for detecting ddos attacks in software-defined networks
(Springer, 2023-03) Haribabu, K.
Software-Defined Network (SDN) is an approach where the network architecture is divided into 3 planes, namely the control plane, the data plane, and the application plane. It represents a major step forward from traditional, hardware-based networking to software-based networking where a programmable central controller, at the control plane, facilitates controlling the routing of data and allows for easier network management and scalability. On the other hand, the architecture makes the controller a target for many malicious attacks, most common of them being Distributed Denial of Service (DDoS) attacks. Thus, to address cybersecurity issues in SDN architecture, we investigated recent studies and trends that used Machine Learning algorithms to detect DDoS attacks in the control plane. We compared popular ML algorithms - k-Nearest Neighbors (k-NN), Support Vector Machine (SVM), Decision Trees (DT), Artificial Neural Network (ANN) - with different feature selection methods: Neighbourhood Component Analysis (NCA), and minimum Redundancy - Maximum Relevance (mRMR). Considering real-time DDoS attack detection, we have proposed an ensemble learning model that outperforms previously proposed models for detecting DDoS attacks. The proposed model utilizes feature selection and is generalized with a 10-Fold Cross Validation Recall of a 100%, F1-Score of 99.9988%, and Accuracy of 99.9990%.
A review on WSN based resource constrained smart IoT systems
(Springer, 2025) Haribabu, K.
In Wireless Sensor Network (i.e. WSN) based resource constrained Internet of Things (i.e. IoT) environments, efficient data forwarding is achieved through cluster based mechanisms, where cluster heads facilitate communication among themselves and with the sink node. Data collected by each cluster head is temporarily buffered before being transmitted to the sink via multi-hop communication. The integration of advanced wireless technologies, such as 5th Generation (i.e. 5G) networks, offers significant benefits, including reduced latency, extensive coverage, improved spectral efficiency, and higher data transmission rates. Incorporating Device-to-Device (i.e. D2D) communication further enhances energy efficiency and offloads data traffic, addressing critical IoT requirements such as low latency, increased network capacity, and improved spectral and energy efficiency. Software Defined Networking (i.e. SDN) addresses diverse IoT network needs across domains like smart grids, healthcare, traffic signaling, agriculture, and smart homes by enabling efficient communication, network management, and innovative control procedures. However, SDN’s application for anomaly detection and primary defense against security threats in IoT systems remains underexplored. This research investigates the potential of the design of an intelligent mechanism for energy efficient, privacy preserving, and secure communication in WSN based resource constrained IoT systems. The proposed approach leverages advanced technologies such as SDN, Machine Learning (i.e. ML), Deep Learning (i.e. DL), D2D communication, Computer Vision, and Network Function Virtualization (i.e. NFV). Additionally, it emphasizes assessing and offloading specific IoT application functions onto the network’s edge to enhance performance. Moreover, the development of lightweight security mechanisms for secure communication in resource constrained IoT environments is also identified as a crucial research domain.
A WSN and vision based energy efficient and smart surveillance system using computer vision and ai at edge
(Springer, 2024-04) Haribabu, K.
The current traditional surveillance systems frequently fall short in delivering satisfactory quality of service, leading to frustrated user experiences. Consequently, there is a growing demand for more efficient and intelligent surveillance solutions. This paper addresses this need by introducing a wireless sensor networking (WSN) and vision based approach that employs optical verification through computer vision and AI at the edge, specifically designed for resource constrained IoT nodes. To support the feasibility and effectiveness of the proposed system, the authors conducted experimental analyses using both simulation and a case study. The results of the study demonstrate that the suggested surveillance system is energy conservative and provides real time information, offering a promising solution to the limitations of traditional surveillance setups.
A WSN and vision based smart, energy efficient, scalable, and reliable parking surveillance system with optical verification at edge for resource constrained IoT devices
(Elsevier, 2024-12) Haribabu, K.
As urbanization accelerates, the demand for efficient parking surveillance solutions has increased. However, existing solutions often face challenges related to energy consumption, scalability, and reliability. This paper introduces a smart hybrid parking surveillance system integrating wireless sensor networks (WSNs) with vision based solution at the edge for resource constrained IoT devices to address these challenges. The solution leverages WSNs for periodic readings of parking space occupancy and introduces a low power sleep mode in the network for energy efficiency, along with optical verification strategies using computer vision models like R-CNN and Faster R-CNN FPN on ResNet50 and MobileNetv2 backbones for distinguishing between true and false positives in the WSN data for a greater accuracy in parking space occupancy. The system utilizes edge for computing on edge servers resulting in increased responsiveness of the system, reduced data transmission and real time processing of data. The proposed solution is formulated in such a way that it automatically switches between WSN and vision based sensing resulting in less energy consumption and longer lifespan of the system without compromising on accuracy. Through experimental results it is observed that models trained on the MobileNetv2 backbone demonstrated at least twice faster for both processing the images and training compared to those models trained on the ResNet backbone. On the other hand, both Faster R-CNN FPN (input resolution: 1440) and R-CNN (input resolution: 128) models trained on the MobileNetv2 backbone have slightly lower accuracies than the same models trained on the ResNet50 backbone.