Detection of Masquerade Attacks by using DDSGA: Data-Driven Semi-Global Alignment Approach with CIDS Framework

Masquerade attackers embody a genuine user to get the user services and advantages. The SGA is very effective as well as especially techniques to find out this attack but it has not stretched the accuracy and executions required by large scale, multiuser systems. To increase whole effectiveness as well as the execution of this algorithm, we suggest the Data Driven Semi-Global Alignment, DDSGA approach. As per the view point of security operative, DDSGA update the scoring systems by adopting various alignment arguments for every user. more ever, it allow small change in user command series by allowing little becoming different in the low-level showing of the command to ability to perform a task. It makes suitable changes in the client using technique by updating the pattern of a user according to its current using technique. For perfecting the runtime located, DDSGA to make as tiny the alignment overhead and parallelizes the find out and the update. After representing the DDSGA phases, we represent the experimental results. This output shows that DDSGA get the high hit ratio of 88.4 % with a low false positive rate. It increases the hit ratio of the enhanced SGA as well as reduces Maxion-Townsend cost. Hence, DDSGA results in increasing all the hit ratio and false positive rates with an capable calculation overhead.