PROJECT TITLE :

Optimal Spot-Checking for Collusion Tolerance in Computer Grids - 2017

ABSTRACT:

Many grid-computing systems adopt voting-based mostly techniques to resist sabotage. However, these techniques become ineffective in grid systems subject to collusion behavior, where some malicious resources will collectively sabotage employment execution by returning identical wrong results. Spot-checking has been used to detect and tackle the collusive issue by sending randomly chosen resources a sure number of spotter jobs with known correct results to estimate resource credibility primarily based on the came back result. This paper makes original contributions by formulating and solving a new spot-checking optimization downside for grid systems subject to collusion attacks, with the target to minimize probability of the real task failure (PGTF, i.e., the incorrect output probability) whereas meeting an expected overhead constraint. The problem answer contains an optimal combination of task distribution policy parameters, as well as the amount of deployed spotter tasks, the amount of resources tested by every spotter task, and the amount of resources assigned to perform the genuine task. The optimization procedure encompasses a new iterative methodology for evaluating system performance metrics of PGTF and expected overhead in terms of the full variety of task assignments. Both mounted and unsure attack parameters are thought-about. Illustrative examples are provided to demonstrate the proposed optimization drawback and solution methodology.