Static Knowledge-Based Authentication Mechanism for Hadoop Distributed Platform using Kerberos

Abstract

With the quickened phenomenal expansion of data, storing massive data has become important and increasingly growing day by day. Thus, big data came to express this large data and handling it properly under three important characteristics such as volume, veracity, and Variety. One practical of big data problems is user and services authentication. Kerberos v5 protocol provided a new solution to such this problem in the Hadoop-distributed platform (HDP). In this paper, we suggest a credible scheme by adding one more level of protection and authentication security to the Kerberos v5 protocol by using a static knowledge-based authentication (SKBA). Where in the login and verification phase by using Kerberos protocol, the KDC will replay with a question to the user-side to check the actual presence of user which the user already answered this question in his registration phase. Our credible scheme is useful in case of capturing messages that enable an eavesdropper to get the ticket that allows getting access to the HDFS as well as to avoid the common attacks with less computation, communication and storage cost. The proposed scheme works seriously and strictly to ensure the registration by delivery of user information over an insecure network in a safe manner and store this information in the KDC-database to be used later for getting access with HDFS.

An authenticated key management scheme for securing big data environment

“…From here comes the importance of getting a unique secret key agreed between the user and the server to use it during communication, where each user will have its own agreed secret key to deal with the server, which symbolized it for the user-A as 𝐾 𝐴,𝑠 . This key is mainly obtained by A and B as a corresponding public key between the user and the server and can by using them calculate the right key, where the following formulas (3) to (6) shows how:…”

“…Table 4 shows the results of the computation cost for AKMS scheme and the works related static knowledge-based authentication mechanism (SKAM) [6], A token-based authentication security (TASS) [25], and A novel authentication framework for Hadoop (NAFH) [23] as well as give a relative comparison regarding the registration phase, Table 5 will do the same for both the login and communication phases. The total computation cost of the registration phase that represents the user and server is 2T H + T E .…”

“…As noted, it is better as compared to other related works. Table 6 shows the communication cost for AKMS scheme and other related works such SKAM [6], TASS [25], and NAFH [23], calculated in the same way and assuming that the same…”

“…It stores (ID, B, b, Pub ID ) in the server database, thus the maximum storage cost is 2368 (2*160 + 2*1024) bits. Table 7 provides the comparison results of AKMS scheme over the related works SKAM [6], TASS [25], and NAFH [23], and shows that the storage cost of AKMS is relatively reasonable and may become less if the keys used are reduced and made smaller. Table 7 are graphically drawn in Figure 5 to clearly show the different storage cost of each work measured in bits.…”

“…Where it became an important and modern topic racing towards researchers as a rich field of research areas and come out with the most prominent researches and thoughts and innovative ways to deal with the problem and cover its gaps [4]. Big data networks today occupy great importance through the offer of usefulness that can be seized by the user in a big data environment [5], [6] where the user can store his data in the cloud service and share it with others [7]. Also, companies and employees can get great convenience by using cloud computing as modern and exclusive technology that is considered as a big data environment.…”