Abstract-Authentication

Abstract-Anartificial intelligence based mutual authentication system with four entities is developed keeping any eye to enhancing threat and hacking in mobile network. Since voice frequency lies between 0 ~ 3.5 KHz, a person talking some specific word in different times is always consisting of a very narrow range of frequencies which are varying person to person. Voice frequency of the salutation or selective words used by a subscriber at the beginning of conversation like Hello, Good Morning, Namaskar etc is taken as first entity for authentication purpose. Second entity is chosen as frequency of flipping or clapping sound of the subscriber at the time of initializing a call. Then third entity is taken as face image of the calling subscriber. We propose fourth entity as probability of salutation or greeting word from subscriber's talking habit (set of salutation words) whiles the subscriber starts a call. These four entities such as probability of particular range of frequencies for the salutation word, frequency of flipping sound, face image matching of the subscriber, particular salutation or greeting word at the time of starting a call are used with most frequently, more frequently and less frequently by the subscriber like uncertainty in Artificial Intelligence (AI). Now different relative grades are assigned for most frequently, more frequently and less frequently used parameters and the grades are modified according to weightage. We invent a Fuzzy Rule (condition) by Fuzzy operation. If the results obtained from fuzzy operations are satisfied by the invented fuzzy rule, the subscriber (MS) and the network (MSC or PDSN) are mutually authenticated in 3-G mobile communications.

No abstract

No abstract

No abstract