Security and Privacy Aspects in MapReduce on Clouds: A Survey

摘要: MapReduce is a programming system for distributed processing large-scale data in an efficient and fault tolerant manner on private, public, or hybrid cloud. extensively used daily around the world as computation tool large class of problems, e.g., search, clustering, log analysis, different types join operations, matrix multiplication, pattern matching, analysis social networks. Security privacy computations are essential concerns when executed public clouds. In order to execute job clouds, authentication mappers-reducers, confidentiality data-computations, integrity correctness-freshness outputs required. Satisfying these requirements shield operation from several attacks computations. this paper, we investigate discuss security challenges requirements, considering variety adversarial capabilities, characteristics scope MapReduce. We also provide review existing protocols their overhead issues.