Ddsga A Data-Driven Semi-Global Alignment

Abstract

A masquerade aggressor impersonates a legal user to utilize the user services and privileges. The semi global alignment algorithmic program (SGA) is one in all the foremost effective and economical techniques to watch these attacks but it isn't reached nonetheless the accuracy and performance required by large scale, multiuser systems. to boost every the effectiveness and additionally the performances of this algorithmic program, we tend to propose the Data-Driven Semi-Global Alignment, DDSGA approach. From the protection effectiveness scan purpose, DDSGA improves the rating systems by adopting distinct alignment parameters for each user. Moreover, it tolerates very {little} mutations in user command sequences by allowing little changes among the low-level illustration of the commands utility. It collectively adapts to changes among the user behaviour by change the signature of a user in line with its current behaviour. To optimize the runtime overhead, DDSGA minimizes the alignment overhead and parallelizes the detection and additionally the update.