PROJECT TITLE :

DDSGA: A Data-Driven Semi-Global Alignment Approach for Detecting Masquerade Attacks

ABSTRACT:

A masquerade attacker impersonates a legal user to utilize the user services and privileges. The semi-global alignment algorithm (SGA) is one amongst the most effective and efficient techniques to detect these attacks but it's not reached nonetheless the accuracy and performance needed by giant scale, multiuser systems. To boost both the effectiveness and also the performances of this algorithm, we have a tendency to propose the information-Driven Semi-International Alignment, DDSGA approach. From the protection effectiveness view purpose, DDSGA improves the scoring systems by adopting distinct alignment parameters for every user. Furthermore, it tolerates little mutations in user command sequences by permitting small changes within the low-level illustration of the commands functionality. It conjointly adapts to changes within the user behaviour by updating the signature of a user consistent with its current behaviour. To optimize the runtime overhead, DDSGA minimizes the alignment overhead and parallelizes the detection and also the update. When describing the DDSGA phases, we tend to gift the experimental results that show that DDSGA achieves a high hit ratio of 88.4 percent with a coffee false positive rate of 1.seven percent. It improves the hit ratio of the enhanced SGA by about 21.nine % and reduces Maxion-Townsend price by 22.five %. Hence, DDSGA results in improving both the hit ratio and false positive rates with an acceptable computational overhead.