Faculty Publications
Permanent URI for this communityhttps://idr.nitk.ac.in/handle/123456789/18736
Publications by NITK Faculty
Browse
11 results
Search Results
Item Split personality malware detection and defeating in popular virtual machines(2012) Kumar, A.V.; Vishnani, K.; Kumar, K.V.Virtual Machines have gained immense popularity amongst the Security Researchers and Malware Analysts due to their pertinent design to analyze malware without risking permanent infection to the actual system carrying out the tests. This is because during analysis, even if a malware infects and destabilizes the guest OS, the analyst can simply load in a fresh image thus avoiding any damage to the actual machine. However, the cat and mouse game between the Black Hat and the White Hat Hackers is a well established fact. Hence, the malware writers have once again raised their stakes by creating a new kind of malware which can detect the presence of virtual machines. Once it detects that it is running on a virtual machine, it either terminates execution immediately or simply hides its malicious intent and continues to execute in a benign manner thus evading its own detection. This category of malware has been termed as Split Personality malware or Analysis Aware malware in the Information Security jargon. This paper aims at defeating the split personality malware in popular virtual machine environment. This work includes first the study of various virtual machine detection techniques and then development of a method to thwart these techniques from successfully detecting the virtual machines-VirtualBox, VirtualPC and VMware. Copyright © 2012 ACM.Item An effective analysis on intrusion detection systems in wireless mesh networks(Institute of Electrical and Electronics Engineers Inc., 2017) Karri, K.G.; Raju, V.P.; Santhi Thilagam, P.S.Intrusion Detection Systems(IDSs) are widely used to detect both known attacks and unknown attacks performed by internal and external attackers in wireless networks. However, challenging issues for developing IDSs inWireless Mesh Networks (WMNs) are 1) supporting interoperability and 2) handling volatile parameters. In addition, security standards for WMN are still in draft stage, and to protect the WMN, IDSs of similar wireless networks such as wireless sensor, Ad-Hoc, MANET can be adopted, but the best performance is not guaranteed. In this paper, we have classified the existing IDSs for wireless networks into four categories namely single layer IDS, cross-layer IDS, reputation-based IDS, reputation based cross-layer IDS, and analyzed the performance of these IDSs with core-layer attacks and detection methodology. Based on our analysis, we address the loopholes in existing IDSs and specify research directions for strengthening the existing IDSs and for developing new efficient IDSs with respect to backbone mesh and client mesh networks. © 2017 IEEE.Item Efficient Traffic Signboard Recognition System Using Convolutional Networks(Springer, 2020) Mothukuri, S.K.P.; Tejas, R.; Patil, S.; Darshan, V.; Koolagudi, S.G.In this paper, a smart automatic traffic sign recognition system is proposed. This signboard recognition system plays a vital role in the automated driving system of transport vehicles. The model is built based on convolutional neural network. The German Traffic Sign Detection Benchmark (GTSDB), a standard open-source segmented image dataset with forty-three different signboard classes is considered for experimentation. Implementation of the system is highly focused on processing speed and classification accuracy. These aspects are concentrated, such that the built model is suitable for real-time automated driving systems. Similar experiments are carried in comparison with the pre-trained convolution models. The performance of the proposed model is better in the aspects of fast responsive time. © Springer Nature Singapore Pte Ltd. 2020.Item Development of Fault Detection Method in Cable Using Arduino UNO(Institute of Electrical and Electronics Engineers Inc., 2022) Bairwa, B.; Rathod, S.; Yaragatti, U.R.; Manohar, K.A.This study provides the investigation of underground cable fault. Fault are classified into two type such as symmetrical and unsymmetrical fault. For this fault detection range of about 1m to 2.6 km of the underground cable have been investigated. In underground cable, fault is validating through live tests as per the research knowledge. The underground cable fault are largely caused due to improper insulation, interweave, mesh and other accessories. symmetrical and unsymmetrical fault are present to detect and classify incipient fault in underground cable at the distribution voltage level. The wavelet transformer approach has been used to detect the fault location of the underground fault. This project deal with number of high voltage cable fault location technique with modeling and simulation. © 2022 IEEE.Item DDoS attacks at the application layer: Challenges and research perspectives for safeguarding web applications(Institute of Electrical and Electronics Engineers Inc., 2019) Praseed, A.; Santhi Thilagam, P.S.Distributed denial of service (DDoS) attacks are some of the most devastating attacks against Web applications. A large number of these attacks aim to exhaust the network bandwidth of the server, and are called network layer DDoS attacks. They are volumetric attacks and rely on a large volume of network layer packets to throttle the bandwidth. However, as time passed, network infrastructure became more robust and defenses against network layer attacks also became more advanced. Recently, DDoS attacks have started targeting the application layer. Unlike network layer attacks, these attacks can be carried out with a relatively low attack volume. They also utilize legitimate application layer requests, which makes it difficult for existing defense mechanisms to detect them. These attacks target a wide variety of resources at the application layer and can bring a server down much faster, and with much more stealth, than network layer DDoS attacks. Over the past decade, research on application layer DDoS attacks has focused on a few classes of these attacks. This paper attempts to explore the entire spectrum of application layer DDoS attacks using critical features that aid in understanding how these attacks can be executed. defense mechanisms against the different classes of attacks are also discussed with special emphasis on the features that aid in the detection of different classes of attacks. Such a discussion is expected to help researchers understand why a particular group of features are useful in detecting a particular class of attacks. © 2018 IEEE.Item Image Analysis of Nuclei Histopathology Using Deep Learning: A Review of Segmentation, Detection, and Classification(Springer, 2023) Kadaskar, M.; Patil, N.Deep learning has recently advanced in its applicability to computer vision challenges, and medical imaging has become the most used technique in histopathology image analysis. Nuclei instance segmentation, detection, and classification are one such task. Reliable analysis of these image slides is critical in cancer identification, treatment, and care. Researchers have recently been interested in this issue. This study reviews the categorization and investigation of strategies utilized in recent works to improve the effectiveness of automated nuclei segmentation, detection, and classification in histopathology images. It critically examines state-of-the-art deep learning techniques, analyzes the trends, identifies the challenges, and highlights and helps with the future directions for research. The taxonomy includes deep learning techniques, enhancement, and optimization methods. The survey findings will help to overcome the challenges of nuclei segmentation, detection, and classification while improving the performance of models and, thus, aid future research plans. © 2023, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.Item Machine learning techniques for periodontitis and dental caries detection: A narrative review(Elsevier Ireland Ltd, 2023) Radha, R.C.; Raghavendra, B.S.; Subhash, B.V.; Rajan, J.; Narasimhadhan, A.V.Objectives: In recent years, periodontitis, and dental caries have become common in humans and need to be diagnosed in the early stage to prevent severe complications and tooth loss. These dental issues are diagnosed by visual inspection, measuring pocket probing depth, and radiographs findings from experienced dentists. Though a glut of machine learning (ML) algorithms has been proposed for the automated detection of periodontitis, and dental caries, determining which ML techniques are suitable for clinical practice remains under debate. This review aims to identify the research challenges by analyzing the limitations of current methods and how to address these to obtain robust systems suitable for clinical use or point-of-care testing. Methods: An extensive search of the literature published from 2015 to 2022 written in English, related to the subject of study was sought by searching the electronic databases: PubMed, Institute of Electrical and Electronics Engineers (IEEE) Xplore, and ScienceDirect. Results: The initial electronic search yielded 1743 titles, and 55 studies were eventually included based on the selection criteria adopted in this review. Studies selected were on ML applications for the automatic detection of periodontitis and dental caries and related dental issues: Apical lessons, Periodontal bone loss, and Vertical root fracture. Conclusion: While most of the ML-based studies use radiograph images for the detection of periodontitis and dental caries, few pieces of the literature revealed that good diagnostic accuracy could be achieved by training the ML model even with mobile photos representing the images of dental issues. Nowadays smartphones are used in every sector for different applications. Training the ML model with as many images of dental issues captured by the smartphone can achieve good accuracy, reduce the cost of clinical diagnosis, and provide user interaction. © 2023 Elsevier B.V.Item Fuzzy Request Set Modelling for Detecting Multiplexed Asymmetric DDoS Attacks on HTTP/2 servers(Elsevier Ltd, 2021) Praseed, A.; Santhi Thilagam, P.S.The introduction of HTTP/2 has led to a dramatic change in web traffic. The steady flow of requests in HTTP/1.1 has been replaced by bursts of multiple requests, largely due to the introduction of multiplexing in HTTP/2 which allows users to send multiple requests through a single connection. This feature was introduced in order to reduce the page loading time by multiplexing a web page and its associated resources in a single connection. While this feature has significantly improved user experience, it can be misused to launch sophisticated application layer DDoS attacks against HTTP/2 servers. Instead of the intended use of multiplexing, attackers can force the web server to process multiple random requests simultaneously, leading to increased server usage. The use of computationally intensive requests can further exacerbate the situation. These attacks, called Multiplexed Asymmetric Attacks, pose a dangerous threat to HTTP/2 servers and stem from the lack of verification of the multiplexed requests. In this work, an approach to model an HTTP/2 request set as a fuzzy multiset is presented. The proposed approach uses a combination of relative cardinality and request workload to detect multiplexed AL-DDoS attacks. Experiments on open source datasets demonstrate that the proposed approach is able to detect multiplexed AL-DDoS attacks with an accuracy of around 95%, while maintaining a low False Positive Rate (FPR) of around 3%. © 2021 Elsevier LtdItem Securing the IoT Application Layer from an MQTT Protocol Perspective: Challenges and Research Prospects(Institute of Electrical and Electronics Engineers Inc., 2024) Lakshminarayana, S.; Praseed, A.; Santhi Thilagam, P.S.The Internet of Things (IoT) is one of the most promising new millennial technologies, having numerous applications in our surrounding environment. The fundamental goal of an IoT system is to ensure effective communication between users and their devices, which is accomplished through the application layer of IoT. For this reason, the security of protocols employed at the IoT application layer are extremely significant. Message Queuing Telemetry Transport (MQTT) is being widely adopted as the application layer protocol for resource-constrained IoT devices. The reason for the widespread usage of the MQTT protocol in IoT devices is its highly appealing features, such as packet-agnostic communication, high scalability, low power consumption, low implementation cost, fast and reliable message delivery. These capabilities of the MQTT protocol make it a potential and viable target for adversaries. Therefore, we initially emphasize on the emerging MQTT vulnerabilities and provide a classification of identified MQTT vulnerabilities for the IoT paradigm. Then, this paper reviews attacks against the MQTT protocol and the corresponding defense mechanisms for MQTT-based IoT deployments. Furthermore, MQTT attacks are categorized and investigated with reference to crucial characteristics that aid in comprehending how these attacks are carried out. The defense mechanisms are discussed in detail, with a particular focus on techniques for identifying vulnerabilities, detecting and preventing attacks against the MQTT protocol. This work also discloses lessons learned by identifying and providing insightful findings, open challenges, and future research directions. Such a discussion is anticipated to propel more research efforts in this burgeoning area and pave a secure path toward expanding and fully realizing the MQTT protocol in IoT technology. © 2024 IEEE.Item Deep learning-based arecanut detection for X-ray radiography: improving performance and efficiency for automated classification and quality control(Taylor and Francis Ltd., 2025) Naik, P.M.; Rudra, B.X-ray radiography is a valuable, non-destructive tool and can be used to examine the internal components or quality attributes of agricultural commodities, including arecanut. The true quality of an arecanut can be determined using destructive methods through visual inspection. However, dissected arecanuts do not have a shelf life. There is no non-destructive method available for grading arecanuts. We employ X-ray imaging as an aid to conduct internal examinations of arecanuts, allowing for thorough inspection without causing damage. A custom X-ray image dataset of arecanuts is created for automated interpretation of grades. We developed a hybrid arecanut grading model using YOLOv5s architecture incorporating the Stem, the GhostNet and the Transformer blocks. The proposed hybrid architecture outperforms in comparison with state-of-the-art models with a mean average precision (mAP) of 97.30%. The proposed 9.5 MB lightweight model can easily fit into X-ray devices, making it ideal for detecting arecanut grades in the industry. This method could transform the standards of quality inspection for arecanut. Its incorporation could establish a new industry benchmark for unparalleled quality assessment using X-ray technology as a non-destructive tool. © 2024 Informa UK Limited, trading as Taylor & Francis Group.