Multicriteria Optimization to Select Images as Passwords in Recognition Based Graphical Authentication Systems

摘要

Usability and guessability are two conflicting criteria in assessing the suitability of an image to be used as password in the recognition based graphical authentication systems (RGBSs). We present the first work in this area that uses a new approach, which effectively integrates a series of techniques in order to rank images taking into account the values obtained for each of the dimensions of usability and guessability, from two user studies. Our approach uses fuzzy numbers to deal with non commensurable criteria and compares two multicriteria optimization methods namely, TOPSIS and VIKOR. The results suggest that VIKOR method is the most applicable to make an objective state-ment about which image type is better suited to be used as password. The paper also discusses some improvements that could be done to improve the ranking assessment.