Conference Papers
Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506
Browse
39 results
Search Results
Item Automated Traffic Light Signal Violation Detection System Using Convolutional Neural Network(Springer, 2020) Bordia, B.; Nishanth, N.; Patel, S.; Anand Kumar, M.; Rudra, B.Automated traffic light violation detection system relies on the detection of traffic light color from the video captured with the CCTV camera, detection of the white safety line before the traffic signal and vehicles. Detection of the vehicles crossing traffic signals is generally done with the help of sensors which get triggered when the traffic signal turns red or yellow. Sometimes, these sensors get triggered even when the person crosses the line or some animal crossover or because of some bad weather that gives false results. In this paper, we present a software which will work on image processing and convolutional neural network to detect the traffic signals, vehicles and the white safety line present in front of the traffic signals. We present an efficient way to detect the white safety line in this paper combined with the detection of traffic lights trained on the Bosch dataset and vehicle detection using the TensorFlow object detection SSD model. © 2020, Springer Nature Singapore Pte Ltd.Item Distributed Adaptive Video Streaming using Inter-Server Data Distribution and Agent-based Adaptive Load Balancing(Institute of Electrical and Electronics Engineers Inc., 2020) Bhowmik, M.; Raghunandan, A.; Rudra, B.As the number and hours of videos available within an organisation increases, as well as it's demand, the need for fast video streaming applications arises. Cloud based services are not cost effective and are not an ideal choice for storing the ever-increasing video data that is usually stored and used only within a particular organisation, like a University. Hence, this paper proposes a web based system design to store and stream videos at a small-scale within an organisation. To improve the video viewing experience for the user, the system is flexible to handle sudden changes, like increase in number of requests. The system requires the use of a cluster of servers to deliver the content as a single server cannot handle the load as number of requests increases. This requires effective load distribution among the servers. This paper proposes a way to design this system for adaptive video streaming. This system is highly scalable and can handle high loads, i.e. a higher number of users connecting to the application simultaneously. This paper proposes an algorithm called inter-server load balancing algorithm with Adaptive Agent-based load balancing to solve this problem. The algorithms also incorporates dynamic video resolution delivery techniques to ensure smooth viewing experience in the whole user experience irrespective of the network speed and bandwidth. © 2020 IEEE.Item Video surveillance for the crime detection using features(Springer, 2021) Chowdhary, A.; Rudra, B.This paper aims at extending the comparison between two images and locating the query image in the source image by matching the features in the videos by presenting a method for the recognition of a particular person or an object. The frames matching the feature (not feature its query) object in a given video will be the output. We describe a method to find unique feature points in an image or a frame using SIFT, i.e., scale-invariant feature transform method. SIFT is used for extracting distinctive feature points which are invariant to image scaling or rotation, presence of noise, changes in image lighting, etc. After the feature points are recognized in an image, the image is tracked for comparison with the feature points found in the frames. The feature points are compared using homography estimation search to find the required query image in the frame. In case the object is not present in the frame, then it will not present any output. © Springer Nature Singapore Pte Ltd 2021.Item Atm theft investigation using convolutional neural network(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Satish, Y.C.; Rudra, B.Image processing in a surveillance video has been a challenging task in research and development for several years. Crimes in Automated Teller Machine (ATM) is common nowadays, in spite of having a surveillance camera inside an ATM as it is not fully integrated to detect crime/theft. On the other hand, we have many image processing algorithms that can help us to detect the covered faces, a person wearing a helmet and some other abnormal features. This paper proposes an alert system, by extracting various features like face-covering, helmet-wearing inside an ATM system to detect theft/crime that may happen. We cannot judge theft/crime as it may happen at any time but we can alert the authorized persons to monitor the video surveillance. © The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd 2021.Item Machine Learning Techniques for the Investigation of Phishing Websites(Springer Science and Business Media Deutschland GmbH info@springer-sbm.com, 2021) Ajaykumar, K.B.; Rudra, B.Phishing is ordinarily acquainted with increase a position in an organization or administrative systems as a zone of a greater assault, similar to an advanced tireless risk (APT) occasion. An association surrendering to such a partner degree assault generally continues serious money related misfortunes furthermore to declining piece of the pie, notoriety, and customer trust. Depending on scope, a phishing attempt may step up into a security episode from that a business can have an inconvenient time recuperating. So as to locate this kind of assault, we endeavored to make a machine learning model that advises the client that it is suspicious or genuine. Phishing sites contain various indications among their substance also, web program-based information. The motivation behind this investigation is to perform different AI-based order for 30 features incorporating Phishing Websites Data in the UC Irvine AI Repository database. For results appraisal, random forest (RF) was contrasted and elective machine learning ways like linear regression (LR), support vector machine (SVM), Naive Bayes (NB), gradient boosting classifier (GBM), artificial neural network (ANN) and recognized to have the most noteworthy exactness of 97.39. © 2021, The Editor(s) (if applicable) and The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Ethereum Blockchain Enabled Secure and Transparent E-Voting(Springer Science and Business Media Deutschland GmbH, 2021) Rao, V.; Singh, A.; Rudra, B.The blockchain’s revolutionary concept is the underlying technology behind the popular examples such as Bitcoin and it now relies on the Web and online services. Nowadays, blockchain is famous for its use in cryptocurrencies, but many fintech activities and routine processes that were done offline can be done using blockchain. Smart contracts are abstract pieces of codes that need to be inserted into the network and enforced as planned in every phase of upgrading blockchains. With the population growing so fast across the globe, e-voting is an emerging online service-related issue. The smart contracts of blockchain enable to have a easy, safe, cheap, secure and transparent e-voting due to which blockchain is one of the top solutions for e-voting. Even in the many blockchains available in the world, Ethereum is one of the most consistent available blockchain and has widespread use because of which it is suitable for e-voting. An e-voting system must ensure that it is secure, as it should not allow duplicated votes and it should be able to protect attendants’ privacy being fully transparent too. In this paper, Ethereum wallets and Solidity language for smart contracts were used to make a sample small scale e-voting application. The blockchain was tested on local blockchain using ganache and ropsten test network. The Ethereum blockchain keeps the records of ballots and votes after an election is held. Users can use Ethereum wallets to directly submit theirs vote and those votes are handled with the consensus of each Ethereum node. © 2021, Springer Nature Switzerland AG.Item Intrusion Detection Techniques for Detection of Cyber Attacks(Springer Science and Business Media Deutschland GmbH, 2021) Ahmed, S.S.; Kankar, M.; Rudra, B.Intrusion detection system (IDS) is a software-related application where we can detect the system or network activities and notice if any suspicious task happens. Excellent broadening and the use of the Internet lift examine the communication and save the digital information securely. Nowadays, attackers use variety of attacks for fetching private data. Most of the IDS techniques, algorithms, and methods assist to find those various attacks. The central aim of the project is to come up with an overall study about the intrusion detection mechanism, various types of attacks, various tools and techniques, and challenges. We used various machine learning algorithms and found performance metrics like accuracy, recall, and F-measure and compared with the existing work. After this research, we got good results that can help to detect the cyber attacks being performed in the network. © 2021, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.Item Software verification using state diagrams(Grenze Scientific Society, 2021) Bhowmik, M.; Chowdhary, A.; Rudra, B.During the development of software, a programmer will commit many logical errors unknowingly such that the software is not in accordance with the requirements. Such logical errors affect the correctness of the software. The requirements specify some important properties of the software and this knowledge about it will allow to know the behavior of the software which can be leveraged to find certain logical errors. This paper proposes a method which helps to find bugs as well as describes a way by which the programmer can specify software requirements. Based on these programmer specified requirements, the system can be automatically used to verify the software. Also, the method proposed in this paper does not need to use the expected result of a test case to verify the software’s correctness. The proposed algorithm completely relies on the requirements specified by the programmer for finding bugs in the software. The software verification process and the algorithm used is explained with the help of a case study. The paper highlights the advantages of the method and algorithm proposed for software verification along with the implementation details. © Grenze Scientific Society, 2021.Item Prevention of webshell attack using machine learning techniques(Grenze Scientific Society, 2021) Satish, Y.C.; Naik, P.M.; Rudra, B.Webshell is a web vulnerability and a security threat to any user or a server that can be accessed by attackers to control our system. And also, they may use our system as a command control device to attack other systems. It is difficult to monitor and identify such threats because attackers always tried to attack in different methods and new technologies. However, we can detect the webshell with Machine Learning Techniques with better accuracy; all we need is more number of samples. With this project, we presented a PHP based webshell detecting model. We used different ML algorithms: Logistic Regression(LR), Random Forest(RF), Support Vector Machine(SVM) and K-Nearest Neighbour(KNN). Addition to this PHP file's standard statistical features, we also added an opcode sequence from the PHP files, consisting of the TF-IDF Vector and the Hash Vector. Depending upon these features, we trained with different machine learning models(SVM, RF, LR, KNN). In these models, we got better results with Random Forest having an accuracy of 96.45\% with a false-positive rate of 3.5\%, which is good results compared to several popular detection techniques. © Grenze Scientific Society, 2021.Item FQDN similarity and cache-miss property based DNS tunneling detection technique(Grenze Scientific Society, 2021) Bhowmik, M.; Chowdhary, A.; Rudra, B.Although there are many effective methods to detect DNS Tunneling attacks, the attacks still happen, and the attackers can mock genuine queries to bypass such checks. However, in data exfiltration, the DNS queries are continuously changing as some part of it represents the data itself. Thus, all such queries would result in a cache miss, and therefore we can use such properties to detect DNS Tunneling attacks. However, relying on this is not enough as it will also have many false positives. To overcome the problem, we propose three criteria-based methods that consider DNS Tunneling queries’ properties and use them to reduce the number of false positives and thus accurately detect DNS Tunneling traffic. We even discussed the bypassing checks in this paper, and they are both costly and require the attacker to make redundant queries. © Grenze Scientific Society, 2021.