Vellore Institute of Technology (VIT) is a private university located in&nbsp;Tamil Nadu, India. Founded in 1984, as Vellore Engineering College, the institution offers 20 undergraduate, 34 postgraduate, four integrated and four research programs. It has campuses in Vellore, Amravati, Bhopal and Chennai.

VIT is one of the top ranked private universities in India according to NIRF, THE and QS Rankings.&nbsp;Govt. of India has recognized&nbsp;VIT, Vellore as an&nbsp;Institution of Eminence. This has allowed VIT to take independent quality initiatives and move up in world ranking.

&nbsp;

&nbsp;

VIT University

Department of Information Technology

School of Information Technology and Engineering

Vellore Campus

VIT Unitversity

International Journal of Social Computing and Cyber-Physical Systems

Implementation of an efficient and intelligent Indian maritime borderline alert system using IoT

The primary vision of developing smart cities is to enable growing technologies in to our daily activities, that will helps us to resolve our daily issues in house management, health care management, traffic management system. Due to the overcrowding of cities and increase in the number of vehicles finding a free space to park vehicles has become a major issue to the drivers especially in peak hours. Though many traditional approaches and technologies are deployed there have been many flaws are suspected and identified. Though lot of solutions has been proposed over the parking solution problems they have certain limitation and constraints over the devices or technology used as well as the cost factor required for implementation. So considering such factors we have proposed a prototype model to experiment our system which can very effectively optimise the parking solution with low-cost parking solutions. Copyright © 2019 Inderscience Enterprises Ltd.

World University root node

World Review of Entrepreneurship, Management and Sustainable Development

A smart parking system using IoT

The detection and classification of malwares in windows executables is an important and demanding task in the field of data mining. The malwares can easily damage the system by creating harm in the user's system, so some of the existing techniques are developed in the traditional works for an accurate malware detection. But, it lacks some major drawbacks such as inaccurate detection, not highly efficient, requires a large amount of time to classify the malware type, and an increased computational complexity. To solve these issues, this article develops an efficient system for detecting the malwares in an Application Programmable Interfaces (APIs), and classifying its type as worms, virus, Trojans, or normal. Initially, the input dataset is preprocessed by normalizing the data, then its upper and lower boundaries are estimated during feature extraction. Furthermore, the Rete algorithm is implemented to generate the rules based on the pattern matching process. Here, the Multi-Dimensional Naïve Bayes Classification (MDNBS) is implemented to classify the malware that occurred in an API call sequences. In experiments, the performance results of the existing and proposed techniques are evaluated and compared based on the measures of True Positive Rate (TPR), False Positive Rate (FPR), precision, recall, f-measure and, accuracy. © 2018 Taylor &amp; Francis Group, LLC.

Journal of Applied Security Research

A New Malware Detection System Using Machine Learning Techniques for API Call Sequences

Detection of malware has become more challenging today because of the advancements and technologies adapted to corrupt the network or the devices. Static, dynamic and hybrid malware detection analysis methods have failed to provide complete malware detection. Hence in this work, a bio inspired sequence alignment method used in bioinformatics to compare the similarity between amino acid sequences in protein structures has been adapted to give the best similarity score to detect malwares. The state of art sequence alignment methods like Smith Water Man Algorithm (SWMA) used in bio informatics suffers from the problem of more memory utilization and computation time which is in the order of n2 ie., (O(n2)) and hence in this work an efficient sequence alignment algorithm (ESSA) has been proposed to address the problem of memory utilization thereby making the memory utilization and computation time to the order of n ie., (O(n)) there by making the detection rate higher. It is also clear from the results that the similarity score is high when the sequence length is small. The accuracy of the prediction rate of malware and benign increases.

International Journal of Intelligent Engineering and Systems

ESAA: Efficient Sequence Alignment Algorithm for Dynamic Malware Analysis in Windows Executable Using API Call Sequence

The social-media plays a key role in every individual's life by anyone's personal views about their liking-ness/disliking-ness. This methodology is a sharp departure from the traditional techniques of inferring interests of a user from the tweets that he/she posts or receives. It is showed that the topics of interest inferred by the proposed methodology are far superior than the topics extracted by state-of-the-art techniques such as using topic models (Labelled LDA) on tweets. Based upon the proposed methodology, a system has been built, "Who is interested in what", which can infer the interests of millions of Twitter users. A novel mechanism is proposed to infer topics of interest of individual users in the twitter social network. It has been observed that in twitter, a user generally follows experts on various topics of his/her interest in order to acquire information on those topics. A methodology based on social annotations is used to first deduce the topical expertise of popular twitter users and then transitively infer the interests of the users who follow them. © Published under licence by IOP Publishing Ltd.

Department of Software and Systems Engineering

Fulltext

IOP Conference Series: Materials Science and Engineering

Finding user personal interests by tweet-mining using advanced machine learning algorithm in R

Collection of enormous amount of data from various organizations, companies, hospitals, banks etc. has led us to uncover useful patterns for decision making. However, preserving privacy while performing data mining is the important consideration to be made. To perform data mining and at the same time preserve privacy is the key research challenge. Rather than simply following policies or guidelines, tools and methods are employed for releasing the data while preserving privacy. In this survey, various attack models and their privacy models for data mining are discussed. © IAEME Publication.

Department of Digital Communications

International Journal of Mechanical Engineering and Technology

A case study on attack models and privacy models in mining medical datasets

In the history of technological advancements in networks and communicating devices, it is mandatory to have efficient mechanisms to detect the malwares before it corrupts the entire network or the device. Researchers have been adapting to various methodologies to detect malwares using static, dynamic and hybrid approaches. The proposed EFE(Efficient Feature Extraction)algorithm provides an efficient way to detect malwares in dynamic environment using API call sequences. It is clear from the findings that the proposed EFE (Efficient Feature Extraction) algorithm outperforms the other methods by providing a high detection rate when it is classified using SVM algorithm. It is also capable of detecting both known and unknown malwares effectively. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

International Journal of Pharmacy and Technology

EFE: Efficient feature extraction algorithm for dynamic malware analysis in windows executables using API call sequence

Software defined network (SDN) is the revolutionary technology in the Networking atmosphere. It finds its roots in programmable network and control-data-infrastructure plane separation which provides network management as well as network automation. This technology encourages programmability of the network which in turns reduces the cost of operation and increases efficiency. The objective of this paper is to study the various investigations going to understand and evaluate SDN characteristics and benefits. In this paper we will be exploring SDN architecture, SDN related taxonomy and challenges SDN implementation face now and in future. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

Survey of software defined network

This Study Focuses on four major goals. First and foremost identify all the possible Evasion techniques and their possible combinations that can result in AET. Identify methodologies and tools that can generate the AET. Secondly, we provide Snort rules for Snort IDS so that the open source IDS can be enhanced to detect the AET. Thirdly, analyse the existing snort pre-processors and Finite State Machine that must be enhanced to support the complex state maintenance created by the AETs. Finally, the last phase would be the testing and evaluation of the enhanced Snort IDS. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

A case study on advanced evasion techniques

The Intrusion Detection System plays a vital role in the security factor of a network. An evasion technique modifies the attacks for evading the network so that the intrusion detection system (IDS) does not recognize it. An Advanced Evasion Techniques(AET) are techniques which evolves new attacks by combining several existing attacks thereby it evades the intrusion detection system. An AET method provides a way for an attacker to obfuscate malicious data and make him penetrate the network defences unnoticed. By combining attacks, the advanced evasions by passes most security solutions making the traffic to look normal. This paper gives a review about the advanced evasion techniques that the attacker uses for evasion. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

A review on advanced evasion techniques

Software Defined Network (SDN) is a developing innovation which actualizes the decoupling of the control plane from the system components, for example, switches or switches and keeps just the information plane with them. This separation provides a more efficient method for development of more complex and advanced applications that are not vendor specific. In SDN, the control plane which decides how to forward the packets is separated from the network elements and hence the forwarding decisions are made only at SDN Controller, with exceptions when the Network Administrator leaves some control functions to the forwarding elements. In this paper, effort has been made to mitigate two major layer two attacks which are common. A Port Blocker and VLAN Application is written and tested in a POX controller based environment all simulated in Mininet and tested to determine their efficacy. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

Layer two firewall in software defined network

Bio inspired computing, is a field which provides various principles encountered in nature for solving/tackling complex problems by using the computational model of the principle. Numerous researches have been done in this area. Bio inspired computing is where the studies have been done in biological field to identify new technique which can be effectively applied in many computer science related problems with mathematical computation. Bio inspired computing is closely related to the field of artificial intelligence. There are many algorithms/principles which effectively provide a new optimization technique. Bio inspired computing is an emerging technique in this era. In which more and more algorithms and techniques are yet to be identified to provide optimal solution to the complex problems. Bio inspired algorithms are experimental and this can be applied when the there is a less knowledge about the problem. These algorithms are inspired by processes observed in nature by the living species. This paper will provide a description about the various evolutionary and emergent algorithms their basic flow of algorithm, applications, advantages and disadvantages. © 2016, International Journal of Pharmacy and Technology. All rights reserved.

Evolutionary algorithm – A review

Background: The progression of malware is on upsurge lately. The architects of malware make it robust and sheath such that it becomes untraceable while running and hence users fall-prey for these malicious software. These malicious software programs developed by attackers are polymorphic and metamorphic which have the capability to alter their code as they propagate. Methods: The existing malware detection and prevention tools need to be enhanced when it comes to these newly developed malwares. So, to prevent this we take a generic approach that integrates the methods and tools which already exist in order to detect the malware with utmost accuracy and efficiency. Findings: The survey on this paper gives a picture to make use of Op-Code frequency and n-gram for feature extraction and efficient way for detecting malware incase gets on to the system by any means. Different authors claim that they five the best results by increasing the true positives and decreasing the False positive rates. Application: Dynamic and Hybrid methods can be used to detect known and unknown malwares.

Indian Journal of Science and Technology

A Dynamic Malware Analysis for Windows Platform - A Survey

Communication between heterogeneous networks became unavoidable. Clustering simplifies the communication. Cluster head is the leader of the cluster. If the cluster head fails or becomes unreachable an alternative efficient algorithm is required to recover from the failure. This proposes the algorithm which initiates the alternative cluster head selection in a heterogeneous environment. © Research India Publications.

Department of Smart Computing

Global Journal of Pure and Applied Mathematics

Self restorative cluster head selection in heterogeneous network

Radio Frequency Identification (RFID) is entirely based on tag identification. Reader identifies a tag by its ID. Collisions occur frequently while reading the passive tags and reader fails to identify the tags sometimes. This will lead to tag-starvation problem. Therefore, an algorithm is developed to address both collisions and tag-starvation problem. This paper uses Query Tree protocol and ALOHA to develop the algorithm. Query Tree protocol is used to address tag-starvation problem and ALOHA to reduce the collisions of passive tags.