Browsing by Author "Uma, M"

Now showing 1 - 10 of 10
  • No Thumbnail Available
    Item
    An Accurate Method for Deteetion of Cyber Attaeks
    (2013) Padmavathi, G; Uma, M
    Due to the rapid growth of wireless local area networks in day-to-day applications detection of cyber attacks have been increasing. In 2012, a survey stated that an organization experiences with an average of 102 attacks every week, whereas 72 attacks and 50 attacks were detected during 2011 and 2010, approxmiately 42% of attacks have increased in a year. In this paper, the dimensionality reduction techniques are used to detect the cyber attacks. The objective of this research work is to extract the meaningful class labels in the data set using linear dimensionality reduction techniques like Principal Components Analysis (PCA), Independent Component Analysis (ICA) and Linear Discriminant analysis (LDA). The experimental study shows that PCA performs better than LDA and ICA. To improve the obtained results the PCA is combined with SVM, where an accuracy rate increases in the detection of cyber attacks.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Computational Intelligence (Cl) - Techniques and Applications
    (2013) Uma, M; Padmavathi, G
    Computational Intelligence is the most promising technique which has been introduced in every field for optimized results. Computational Intelligence is a set of processing technique which is capable of handling the real world problems. The aim of this review paper is to analyze computational intelligence feature, various branches of it and detailed study about its wide range of applications is analyzed. Applications of Computational Intelligence discussed in this paper itself shows versatility of computational intelligence in this modern society. Computational intelligence plays major role in the field of research because of its capability of adopting the real world problems and which produces the optimized results.
  • No Thumbnail Available
    Item
    An Efficient Data Chunking Non-Sequential Storage to Defend Against Cyber Attacks
    (2014) Uma, M; Padmavathi, G
    The importance of secure data storage in day to day life is increasing rapidly in our society. Data chunking and decentralization plays a significant role in efficiently storing and securing the data. In this research work, server based application is developed using content defined chunking for splitting the content of the files uploaded, inarkov chain for state transition. Secure Hash Algorithm (SHA-512) is used key generation and Advanced Encryption Standard (AES) algorithm is used for encryption and deci-yption of the file chunked. The standard way of storing the chunked file into the server in a sequential order is rearranged and introduced a new method say non-scqiicntial way of storing the chunked flics into the server. The proposed method outperforms than the existing method and the proposed method is evaluated in terms of performance metrics like False acceptance rate, false rejection rate, and attack detection rate. The proposed method is implemented using Java 1.7 as front end and mysql as backend.
  • No Thumbnail Available
    Item
    Enhanced Click dynamics to Ensure User Authentication and Detection of Cyber Attacks
    (2015) Uma, M; Padmavathi, G
    Recently biometric sought more attention in the fie ld o f research and development. Mouse dynamics otherwise known as click dynamics is a biometric system which plays a predominant role in the fie ld o f network security. In this paper, enhanced click dynamics is introduced to ensure user authentication. Vie unknown cyber attack detection process is developed using biometric system. In this research work “anytime algorithm" is integrated along with existing method to increase the accuracy in detecting the unauthorized user i.e., cyber attacks. To evaluate the accuracy in detecting the unknown cyber attacks by the proposed m ethod the experiments were conducted with few performance metrics namely False Acceptance Rate, False Rejection Rale, Authentication time and Attack Detection rate. Vie experiments were conducted f o r 24 participants. Ih e proposed method is developed using JAVA 1.7 a s front end and mysql as b ack end.
  • No Thumbnail Available
    Item
    Enhanced Decoy based Moving Target Defense Mechanism with Improved Quality of Service to Handle Cyber Attacks in Wireless Networks
    (2014) Padmavathi, G; Uma, M
    Cyber attacks are becoming a major challenge in today’s connected environment. More personal devices are connected and operated in a wireless environment. Securing the wheless network needs better solutions in terms of its quality of service. There are many methods available in the literature to handle cyber attacks. Moving target defense mechanism is one of the upcoming and promising mechanisms to handle cyber attacks. Decoys, one of few moving target defense mechanism that is rarely explored. Time triggered approach and Event triggered approach are the two current approaches that dynamically help to secure the data in decoys defense type. The very important aspect to be noted here is that most of the methods provide security with compromised Quality of Service. To overcome this, while handling cyber attacks, an integrated time and event triggered method with AntNet protocol is proposed. The key feature of the proposed method is to defend the wireless networks against cyber attacks and to ensure Quality of Service (QoS) while handling the attacks. The effectiveness of this system is validated by conducting various experiments. The proposed method can identify the unauthorised user i.e. attacks in a precise way. The performance of the proposed method is evaluated based on the metrics like end to end delay, thi'oughput, routing overheads, packet delivery ratio, latency and energy consumption. The proposed methodology is tested in a simulated environment with Linux Fedora and Network Simulator NS2 version ns-allinone-2.35.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    Enhanced Secure Hash based Client Puzzle approach to defend against Cyber Attacks
    (2015) Uma, M; Padmavathi, G
    Game theory is a widely used technique for network security. As technology grows, the cyber worlds are more vulnerable to unknown cyber attacks. There are many cyber attack detection methods available for known attacks; however, efficient methods are essential to detect the unknown cyber attacks. In this research work, an enhanced hash based game theory approach is introduced to defend against cyber attacks. The proposed method is tested in a simulated environment and the method is evaluated using the performance metrics like Throughput, End to end delay. Packet delivery ratio, routing overhead, energy consumption and latency.
  • No Thumbnail Available
    Item
  • No Thumbnail Available
    Item
    A Survey on Various Cyber Attaeks and Their Classifieation
    (2013) Uma, M; Padmavathi, G
    The role of computers and the Internet in modern society is well recognized. Recent developments in the fields of networking and cyberspace have greatly benefited mankind, but the rapid growth of cyberspace has also contributed to unethical practices by individuals who are bent on using the technology to exploit others. Such exploitation of cyberspace for the purpose of accessing unauthorized or secure information, spying, disabling of networks and stealing both data and money is termed as cyber attack. Such attacks have been increasing in number and complexity over the past few years. There has been a dearth of knowledge about these attacks which has rendered many individuals/agencies/organizations vulnerable to these attacks. [7] Hence there is a need to have comprehensive understanding of cyber attacks and its classification. The purpose of this survey is to do a comprehensive study of these attacks in order to create awareness about the various types of attacks and their mode of action so that appropriate defense measures can be initiated against such attacks.